ai for finding research papers

A free, AI-powered research tool for scientific literature

• Sossina M. Haile

New & Improved API for Developers

Introducing semantic reader in beta.

Stay Connected With Semantic Scholar Sign Up What Is Semantic Scholar? Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.

The best AI tools for research papers and academic research (Literature review, grants, PDFs and more)

As our collective understanding and application of artificial intelligence (AI) continues to evolve, so too does the realm of academic research. Some people are scared by it while others are openly embracing the change. 

Make no mistake, AI is here to stay!

Instead of tirelessly scrolling through hundreds of PDFs, a powerful AI tool comes to your rescue, summarizing key information in your research papers. Instead of manually combing through citations and conducting literature reviews, an AI research assistant proficiently handles these tasks.

These aren’t futuristic dreams, but today’s reality. Welcome to the transformative world of AI-powered research tools!

The influence of AI in scientific and academic research is an exciting development, opening the doors to more efficient, comprehensive, and rigorous exploration.

This blog post will dive deeper into these tools, providing a detailed review of how AI is revolutionizing academic research. We’ll look at the tools that can make your literature review process less tedious, your search for relevant papers more precise, and your overall research process more efficient and fruitful.

I know that I wish these were around during my time in academia. It can be quite confronting when trying to work out what ones you should and shouldn’t use. A new one seems to be coming out every day!

Here is everything you need to know about AI for academic research and the ones I have personally trialed on my Youtube channel.

Best ChatGPT interface – Chat with PDFs/websites and more

I get more out of ChatGPT with HeyGPT . It can do things that ChatGPT cannot which makes it really valuable for researchers.

Use your own OpenAI API key ( h e re ). No login required. Access ChatGPT anytime, including peak periods. Faster response time. Unlock advanced functionalities with HeyGPT Ultra for a one-time lifetime subscription

AI literature search and mapping – best AI tools for a literature review – elicit and more

Harnessing AI tools for literature reviews and mapping brings a new level of efficiency and precision to academic research. No longer do you have to spend hours looking in obscure research databases to find what you need!

AI-powered tools like Semantic Scholar and elicit.org use sophisticated search engines to quickly identify relevant papers.

They can mine key information from countless PDFs, drastically reducing research time. You can even search with semantic questions, rather than having to deal with key words etc.

With AI as your research assistant, you can navigate the vast sea of scientific research with ease, uncovering citations and focusing on academic writing. It’s a revolutionary way to take on literature reviews.

• Elicit –  https://elicit.org
• Supersymmetry.ai: https://www.supersymmetry.ai
• Semantic Scholar: https://www.semanticscholar.org
• Connected Papers –  https://www.connectedpapers.com/
• Research rabbit – https://www.researchrabbit.ai/
• Laser AI –  https://laser.ai/
• Litmaps –  https://www.litmaps.com
• Inciteful –  https://inciteful.xyz/
• Scite –  https://scite.ai/
• System –  https://www.system.com

If you like AI tools you may want to check out this article:

• How to get ChatGPT to write an essay [The prompts you need]

AI-powered research tools and AI for academic research

AI research tools, like Concensus, offer immense benefits in scientific research. Here are the general AI-powered tools for academic research. 

These AI-powered tools can efficiently summarize PDFs, extract key information, and perform AI-powered searches, and much more. Some are even working towards adding your own data base of files to ask questions from. 

Tools like scite even analyze citations in depth, while AI models like ChatGPT elicit new perspectives.

The result? The research process, previously a grueling endeavor, becomes significantly streamlined, offering you time for deeper exploration and understanding. Say goodbye to traditional struggles, and hello to your new AI research assistant!

• Bit AI –  https://bit.ai/
• Consensus –  https://consensus.app/
• Exper AI –  https://www.experai.com/
• Hey Science (in development) –  https://www.heyscience.ai/
• Iris AI –  https://iris.ai/
• PapersGPT (currently in development) –  https://jessezhang.org/llmdemo
• Research Buddy –  https://researchbuddy.app/
• Mirror Think – https://mirrorthink.ai

AI for reading peer-reviewed papers easily

Using AI tools like Explain paper and Humata can significantly enhance your engagement with peer-reviewed papers. I always used to skip over the details of the papers because I had reached saturation point with the information coming in. 

These AI-powered research tools provide succinct summaries, saving you from sifting through extensive PDFs – no more boring nights trying to figure out which papers are the most important ones for you to read!

They not only facilitate efficient literature reviews by presenting key information, but also find overlooked insights.

With AI, deciphering complex citations and accelerating research has never been easier.

• Open Read –  https://www.openread.academy
• Chat PDF – https://www.chatpdf.com
• Explain Paper – https://www.explainpaper.com
• Humata – https://www.humata.ai/
• Lateral AI –  https://www.lateral.io/
• Paper Brain –  https://www.paperbrain.study/
• Scholarcy – https://www.scholarcy.com/
• SciSpace Copilot –  https://typeset.io/
• Unriddle – https://www.unriddle.ai/
• Sharly.ai – https://www.sharly.ai/

AI for scientific writing and research papers

In the ever-evolving realm of academic research, AI tools are increasingly taking center stage.

Enter Paper Wizard, Jenny.AI, and Wisio – these groundbreaking platforms are set to revolutionize the way we approach scientific writing.

Together, these AI tools are pioneering a new era of efficient, streamlined scientific writing.

• Paper Wizard –  https://paperwizard.ai/
• Jenny.AI https://jenni.ai/ (20% off with code ANDY20)
• Wisio – https://www.wisio.app

AI academic editing tools

In the realm of scientific writing and editing, artificial intelligence (AI) tools are making a world of difference, offering precision and efficiency like never before. Consider tools such as Paper Pal, Writefull, and Trinka.

Together, these tools usher in a new era of scientific writing, where AI is your dedicated partner in the quest for impeccable composition.

• Paper Pal –  https://paperpal.com/
• Writefull –  https://www.writefull.com/
• Trinka –  https://www.trinka.ai/

AI tools for grant writing

In the challenging realm of science grant writing, two innovative AI tools are making waves: Granted AI and Grantable.

These platforms are game-changers, leveraging the power of artificial intelligence to streamline and enhance the grant application process.

Granted AI, an intelligent tool, uses AI algorithms to simplify the process of finding, applying, and managing grants. Meanwhile, Grantable offers a platform that automates and organizes grant application processes, making it easier than ever to secure funding.

Together, these tools are transforming the way we approach grant writing, using the power of AI to turn a complex, often arduous task into a more manageable, efficient, and successful endeavor.

• Granted AI – https://grantedai.com/
• Grantable – https://grantable.co/

Free AI research tools

There are many different tools online that are emerging for researchers to be able to streamline their research processes. There’s no need for convience to come at a massive cost and break the bank.

The best free ones at time of writing are:

• Elicit – https://elicit.org
• Connected Papers – https://www.connectedpapers.com/
• Litmaps – https://www.litmaps.com ( 10% off Pro subscription using the code “STAPLETON” )
• Consensus – https://consensus.app/

Wrapping up

The integration of artificial intelligence in the world of academic research is nothing short of revolutionary.

With the array of AI tools we’ve explored today – from research and mapping, literature review, peer-reviewed papers reading, scientific writing, to academic editing and grant writing – the landscape of research is significantly transformed.

The advantages that AI-powered research tools bring to the table – efficiency, precision, time saving, and a more streamlined process – cannot be overstated.

These AI research tools aren’t just about convenience; they are transforming the way we conduct and comprehend research.

They liberate researchers from the clutches of tedium and overwhelm, allowing for more space for deep exploration, innovative thinking, and in-depth comprehension.

Whether you’re an experienced academic researcher or a student just starting out, these tools provide indispensable aid in your research journey.

And with a suite of free AI tools also available, there is no reason to not explore and embrace this AI revolution in academic research.

We are on the precipice of a new era of academic research, one where AI and human ingenuity work in tandem for richer, more profound scientific exploration. The future of research is here, and it is smart, efficient, and AI-powered.

Before we get too excited however, let us remember that AI tools are meant to be our assistants, not our masters. As we engage with these advanced technologies, let’s not lose sight of the human intellect, intuition, and imagination that form the heart of all meaningful research. Happy researching!

Thank you to Ivan Aguilar – Ph.D. Student at SFU (Simon Fraser University), for starting this list for me!

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Press ESC to close

Or check our popular categories....

Top 10 AI Tools For Academics: Level Up Your Research

If you aren’t using AI to augment your academic research in 2023, you are wasting a lot of time – time that you could free up from grunt work and invest in the more interesting stuff. 

AI tools have proliferated since the launch of GPT 3 and beyond. The sudden and simultaneous rise of so many consumable AI-powered tools has quickly muddied the waters and made it tiresome if not impossible to get your hands on the right set of AI tools for researchers. 

Fear not! I have hand-picked (I’ve had help, a lot of it, to be honest) 10 of the best AI tools for researchers. Go through the list, combine multiple tools, and create a customized stack of AI tools to help with your research process.

Top 10 AI tools for researchers

We’ll discuss tools powered by artificial intelligence that can augment your research work, save you a lot of time through the automation of certain tasks, and help you brainstorm new ideas avoid plagiarism, and streamline the research process. 

1. PDFgear Copilot

This PDF editor with a humble-looking website doesn’t even market itself properly as a top-class AI tool for researchers. It just is. PDFgear offers you some very simple functionalities that are going to save you a lot of time in different stages of your research activities.

It will let you upload PDF files and give you a summary of what’s inside the PDF . If you think it has missed something, ask. And it will find you the specific piece of information you were worried about. You can even ask PDFgear to compress a file, delete some pages, and perform other small-time edits via chat. 

Now, let’s say you have created a paper and you want to check it for errors before submitting it. Run it through PDFgear. The AI copilot will catch your typos and spelling errors and save you from embarrassment. 

PDFgear is free. It doesn’t matter if you want to summarize one file or 500 files. It’s free and instantaneous. 

The only downside is that this tool is available for download only on Windows 10/11. Nonetheless, the website says the MacOS version will arrive soon.        

2. Consensus

Consensus is useful for everyone and invaluable for researchers. It is an AI-powered search engine that takes questions in natural language and finds evidence-based answers from peer-reviewed research papers . Let that sink in.

While Google invests a lot in understanding the intent behind a search and providing the best answer, as a researcher you know how frustrating Google searches can be. You have to wade through an ocean of unverified content to reach evidence-based answers unless you are a master of keyword matching.

• Consensus helps you access information spread across 200 million peer-reviewed papers.
• They’ll cite the sources while answering your questions.
• Every answer is evidence-based
• The tool offers instant summaries and analyses with the help of GPT 4 and other powerful LLM

When it comes to using AI to augment research work, this is the real deal. You can use Consensus for research without paying a dime. The free edition will even let you create 3 summaries a month. For a price of $7.99 per month, you can generate unlimited summaries powered by GPT4. 

Scite, just like Consensus and PDFgear, has a very simple but elegant offering for researchers, students, and scholars. It tells you where an article has been cited and whether the citing article affirms or disputes the citation. So, as a researcher and a smart individual, you already know why this is incredible. I’ll talk about it a little anyway.

Scite helps you find how older research publications have been cited by newer research work through a feature called Smart Citation. This feature allows you to visualize a network of citations stemming from a single piece of work. It identifies the context of the citation and also classifies the citations as affirmative or negative. 

You can take a glance at the visualization and instantly prioritize the publications that you want to go through . Scite is a real stress buster that can also open your eyes to new research angles. 

These really are exciting times for researchers.

4. SciSpace  

SciSpace is an AI-based tool that simplifies difficult concepts for you. So, if you are in a hurry and need to extract the gist of a sizable scientific paper , drop it at SciSpace and let the Copilot create a summary for you. 

What if you have read an entire paper and cannot make sense of a specific section? Upload the file at SciSpace and highlight the section you need help with. The tool will break it down into digestible chunks and even take follow-up questions from you.

SciSpace also helps you with your literature reviews by finding related articles. 

5. Wordvice AI

Wordvice AI is a well-rounded AI-powered writing assistant. It proofreads your work and checks your articles for spelling, punctuation, and style error. It helps you maintain a flow of writing by analyzing sentence structures and offering sentence-level suggestions.

It will help you choose better words and create better sentences, all while ensuring the correctness of spelling, grammar, and style.  

Wordvice has solid use cases in academic research as well as in the corporate sector. It will help marketers write better copy and sales executives compose better emails. 

If you look closely, most of the AI tools for research can actually be repurposed for other functionalities. Similarly, AI apps meant for business can be repurposed for research. 

6. ChatGPT   

ChatGPT is the OG generative AI chatbot. It took the world by storm and reached 1 million users in 5 days. It represents everything that’s cool about chatbots. But can you use it reliably for research? 

The answer is no. ChatGPT is not considered a credible source for conducting research in any field. It comes up with false citations, offers misinformation, and isn’t up-to-date. 

Then why is ChatGPT included in this list?

For two reasons: 

• It is excellent at taking scattered information and forming comprehensive summaries.
• Its capability to adapt to a certain style of writing is almost magical.

So, as a smart individual what you can do is, get the information from credible sources, tie them up neatly with multiple prompts, and use ChatGPT to transform information into literature.

Also read: ChatGPT Wrappers: Compared [Use ChatGPT for Almost Free]

7. Research Rabbit

They call it “Spotify for Papers” and there is good reason behind it. ResearchRabbit allows you to create a collection of papers much like a Spotify playlist. Then, based on what you add to your collection and how you interact with papers, the platform creates recommendations. How neat is that? It’s like the AI-powered tool is reading your mind to help you read better. 

Paper recommendations aside, ResearchRabbit also creates visualizations featuring your favorite articles showing how they’re cited. It gives you jumping-off points to delve deeper into an idea or to explore a different research angle.   

You cannot call Research Rabbit a research assistant in its traditional sense. It is more like a friend that nudges you to try something new – relevant papers in this case. 

Here is another tool that’s never been marketed as an AI tool for researchers. In fact, Bit.ai is a fully-fledged document-sharing tool designed to cater to corporate needs. Nevertheless, it has certain features that researchers who like to collaborate can leverage.

This tool allows you to integrate a vast range of media items with your document . You can add infographics, create polls, and insert charts, and surveys. When you embed a link, Bit creates interactive visual cards visible to everyone sharing a document.

You can save all kinds of digital assets on the platform so that you do not have to search for content from different sources.

Now, imagine a scenario where you are part of a team of researchers who are collaborating on a few papers. You can organize and orchestrate the entire collaborative process with the help of Bit.ai. 

Zotero is a well-rounded AI research assistant. It helps researchers search better, organize better, and write better. Zotero analyzes your browsing patterns and senses when you are doing research. It then helps you find, sort, and save specific articles.

As you write the AI model recognizes the sources you are referencing and cites them for you following any of the 10000 citing procedures that it supports.

It creates a bibliography of all the resources used in your research paper. It synchronizes your data across devices to ensure access from anywhere at any time.

10. Semantic Scholar

A search engine that helps you search from a database of 213 million scientific papers for free. It is somewhat similar to Consensus except for the fact that it is completely free. The platform is developed by Allen Institute for AI and it aims to make scientific literature accessible to all scholars .

As a researcher,

You can use Semantic Scholar to stay up-to-date with the latest scientific breakthroughs  

Extract meaning and identify connections within papers 

Find the highly influential citations at a glance 

Create an online library to organize all your material

Get paper recommendations

AI tools for researchers that didn’t make the list

 An AI research assistant that helps you find papers, extract meaning, and summarize articles.

A sentence structure checker and proofreader designed with scholastic compositions in mind.

Users can use this tool to converse with PDFs. They can get summaries, ask questions, and find insights into PDF files by uploading them.

iThenticate

A plagiarism-checker designed specifically for research works and scholastic literature.

Scholarcy is a platform driven by AI that helps you analyze scientific articles, extract key information, create lay summaries, and more.  

Maintaining academic integrity while using AI tools for research

While using AI-powered research tools is hardly a matter of choice anymore, it is important to maintain the ethics and standards we associate with academic research. Despite the use of cutting-edge AI, your research procedures should be transparent. 

Best practices for AI-powered academic research

• Mention the use of AI in your research and give credit to the developers.
• Discuss your use of AI tools and how their usage may have impacted the research outcome. 
• Make sure that AI tools are used adhering to data privacy and informed consent requirements.
• Do not use AI-generated content in your research work without due attribution.
• Subject AI-assisted work to rigorous peer review.

FAQs about best AI tools for researchers

Does using ai tools for research raise any ethical concerns.

Yes, there can be concerns regarding data privacy, biased outcome, attribution of credit, and plagiarism. Researchers must be mindful of these issues while involving AI in their research strategy.

Can AI research assistants be used with AI expertise? 

Most AI research assistants come with a conversational AI model that doesn’t require any expertise to use.

Is there an AI-based tool for historical research?

You can use general-purpose AI text analyzers to summarize large volumes of historical texts and create summaries. While there are AI-powered applications trained on historical data, they are mostly gamified, and cannot be directly used in historical research. 

Categorized in:

Share Article:

Saumick Basu

Technical Writer & AI Researcher @ Foundr.AI

Saumick has been writing on technology for half a decade now. He loves talking about cybersecurity, AI, and enjoys diving deep into all disruptive tech. When not writing about tech, he writes songs and plays the drums.

Leave a Reply Cancel reply

Save my name, email, and website in this browser for the next time I comment.

Related Articles

10 best ai tools for recruiting in 2024, top 9 best ai tools for ecommerce in 2024, 9 best ai presentation maker tools [+1 bonus], 10 best ai tools for product managers.

Analyze research papers at superhuman speed

Search for research papers, get one sentence abstract summaries, select relevant papers and search for more like them, extract details from papers into an organized table.

Find themes and concepts across many papers

Don't just take our word for it.

Tons of features to speed up your research

Upload your own pdfs, orient with a quick summary, view sources for every answer, ask questions to papers, research for the machine intelligence age, pick a plan that's right for you, get in touch, enterprise and institutions, custom pricing, common questions. great answers., how do researchers use elicit.

Over 800,000 researchers have tried Elicit already. Researchers commonly use Elicit to:

• Speed up literature review
• Find papers they couldn’t find elsewhere
• Automate systematic reviews and meta-analyses
• Learn about a new domain

Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning.

What is Elicit not a good fit for?

Elicit does not currently answer questions or surface information that is not written about in an academic paper. It tends to work less well for identifying facts (e.g. “How many cars were sold in Malaysia last year?”) and theoretical or non-empirical domains.

What types of data can Elicit search over?

Elicit searches across 200 million academic papers from the Semantic Scholar corpus, which covers all academic disciplines. When you extract data from papers in Elicit, Elicit will use the full text if available or the abstract if not.

How accurate are the answers in Elicit?

A good rule of thumb is to assume that around 90% of the information you see in Elicit is accurate. While we do our best to increase accuracy without skyrocketing costs, it’s very important for you to check the work in Elicit closely. We try to make this easier for you by identifying all of the sources for information generated with language models.

What is Elicit Plus?

Elicit Plus is Elicit's subscription offering, which comes with a set of features, as well as monthly credits. On Elicit Plus, you may use up to 12,000 credits a month. Unused monthly credits do not carry forward into the next month. Plus subscriptions auto-renew every month.

What are credits?

Elicit uses a credit system to pay for the costs of running our app. When you run workflows and add columns to tables it will cost you credits. When you sign up you get 5,000 credits to use. Once those run out, you'll need to subscribe to Elicit Plus to get more. Credits are non-transferable.

How can you get in contact with the team?

Please email us at [email protected] or post in our Slack community if you have feedback or general comments! We log and incorporate all user comments. If you have a problem, please email [email protected] and we will try to help you as soon as possible.

What happens to papers uploaded to Elicit?

When you upload papers to analyze in Elicit, those papers will remain private to you and will not be shared with anyone else.

How accurate is Elicit?

Training our models on specific tasks, searching over academic papers, making it easy to double-check answers, save time, think more. try elicit for free..

AI Search Engine for Research

Consensus is a search engine that uses AI to find insights in research papers

& start searching now!

Why Consensus?

Consensus responsibly uses AI to help you conduct effective research

Search through over 200 million scientific papers without having to keyword match

All of our results are tied to actual studies, we cite our sources and we will never show you ads

Proprietary and purpose-built features that leverage GPT4 and other LLMs to summarize results for you

Used by researchers at the world’s top institutions

researchers, students, doctors, professionals and evidence-conscious consumers choose Consensus

Consensus has been Featured in

Consensus helps.

Find supporting evidence for your paper

Researchers

Efficiently conduct literature reviews

Quickly find answers to patients’ questions

Instantly find expert quotes for presentations

Content Creators

Source peer-reviewed insights for your blog

Health and fitness enthusiasts

Check the viability of supplements and routines

Consensus vs ChatGPT

ChatGPT is built to have a conversation with you. Consensus is purpose-built to help you conduct effective research.

Results pulled directly from peer-reviewed studies

Fully machine-generated, trained on the entire internet

Our mission is to democratize expert knowledge

Sign up for our free BETA

Ask a question, get an answer backed by real research

1.2b citation statements extracted and analyzed

187 m articles, book chapters, preprints, and datasets.

Trusted by leading Universities, Publishers, and Corporations across the world.

Read what research articles say about each other

scite is an award-winning platform for discovering and evaluating scientific articles via Smart Citations. Smart Citations allow users to see how a publication has been cited by providing the context of the citation and a classification describing whether it provides supporting or contrasting evidence for the cited claim.

Extracted citations in a report page

Never waste time looking for and evaluating research again.

Our innovative index of Smart Citations powers new features built to make research intuitive and trustworthy for anyone engaging with research.

Search Citation Statements

Find information by searching across a mix of metadata (like titles & abstracts) as well as Citation Statements we indexed from the full-text of research articles.

Create Custom Dashboards

Build and manage collections of articles of interest -- from a manual list, systematic review, or a search -- and get aggregate insights, notifications, and more.

Reference Check

Evaluate how references from your manuscript were used by you or your co-authors to ensure you properly cite high quality references.

Journal Metrics

Explore pre-built journal dashboards to find their publications, top authors, compare yearly scite Index rankings in subject areas, and more.

Large Language Model (LLM) Experience for Researchers

Assistant by scite gives you the power of large language models backed by our unique database of Smart Citations to minimize the risk of hallucinations and improve the quality of information and real references.

Use it to get ideas for search strategies, build reference lists for a new topic you're exploring, get help writing marketing and blog posts, and more.

Assistant is built with observability in mind to help you make more informed decisions about AI generated content.

Here are a few examples to try:

"How many rats live in NYC?"

"How does the structure of a protein affect its function?"

Awards & Press

Trusted by researchers and organizations around the world

Over 650,000 students, researchers, and industry experts use scite

See what they're saying

scite is an incredibly clever tool. The feature that classifies papers on whether they find supporting or contrasting evidence for a particular publication saves so much time. It has become indispensable to me when writing papers and finding related work to cite and read.

Emir Efendić, Ph.D

Maastricht University

As a PhD student, I'm so glad that this exists for my literature searches and papers. Being able to assess what is disputed or affirmed in the literature is how the scientific process is supposed to work, and scite helps me do this more efficiently.

Kathleen C McCormick, Ph.D Student

scite is such an awesome tool! It’s never been easier to place a scientific paper in the context of the wider literature.

Mark Mikkelsen, Ph.D

The Johns Hopkins University School of Medicine

This is a really cool tool. I just tried it out on a paper we wrote on flu/pneumococcal seasonality... really interesting to see the results were affirmed by other studies. I had no idea.

David N. Fisman, Ph.D

University of Toronto

Do better research

Join scite to be a part of a community dedicated to making science more reliable.

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

[email protected]

334 Leonard St

Brooklyn, NY 11211

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Copyright © 2024 scite LLC. All rights reserved.

Made with 💙 for researchers

Part of the Research Solutions Family.

• Research Guides
• University Libraries

AI-Based Literature Review Tools

• Dialogues: Insightful Facts
• How to Craft Prompts
• Plugins / Extensions for AI-powered Searches
• Cite ChatGPT in APA / MLA
• AI and Plagiarism
• ChatGPT & Higher Education
• Author Profile

Selected AI-Based Literature Review Tools

Updates: See news or release of AI (Beta) across various academic research databases including Web of Science , Scopus , Ebsco , ProQues t, OVID , Dimensions , JStor , Westlaw , and LexisNexis . ********* ********** ********** ********** **********   

Disclaimer: TAMU libraries do not have subscription access to the AI-powered tools listed below the divider line. The guide serves solely as an informational resource. It is recommended that you assess these tools and their usage methodologies independently. ------------------------------------------------------------------------------------------------------------------------------------------------------------- SEMANTIC SCHOLAR

• SCIENTIFIC LITERATURE SEARCH ENGINE - finding semantically similar research papers.
• " A free, AI-powered research tool for scientific literature."  <https://www.semanticscholar.org/>. But login is required in order to use all functions.
• Over 200 millions of papers from all fields of science, the data of which has also served as a wellspring for the development of other AI-driven tools.

The 4000+ results can be sorted by Fields of Study, Date Range, Author, Journals & Conferences

Save the papers in your Library folder. The Research Feeds will recommend similar papers based on the items saved.

Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality Total Citations: 22,438   [Note: these numbers were gathered when this guide was created] Highly Influential Citations 2,001 Background Citations 6,109 Methods Citations 3,273  Results Citations 385

TLDRs (Too Long; Didn't Read) Try this example . Press the pen icon to reveal the highlighted key points . TLDRs "are super-short summaries of the main objective and results of a scientific paper generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is available in beta for nearly 60 million papers in computer science, biology, and medicine..." < https://www.semanticscholar.org/product/tldr>

• AI-POWERED RESEARCH ASSISTANT - finding papers, filtering study types, automating research flow, brainstorming, summarizing and more.
• " Elicit is a research assistant using language models like GPT-3 to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table."   <https://elicit.org/faq#what-is-elicit.>; Find answers from 175 million papers. FAQS
• Example - How do mental health interventions vary by age group?    /   Fish oil and depression Results: [Login required] (1) Summary of top 4 papers > Paper #1 - #4 with Title, abstract, citations, DOI, and pdf (2) Table view: Abstract / Interventions / Outcomes measured / Number of participants (3) Relevant studies and citations. (4) Click on Search for Paper Information to find - Metadata about Sources ( SJR etc.) >Population ( age etc.) >Intervention ( duration etc.) > Results ( outcome, limitations etc.) and > Methodology (detailed study design etc.) (5) Export as BIB or CSV
• How to Search / Extract Data / List of Concept Search -Enter a research question >Workflow: Searching > Summarizing 8 papers> A summary of 4 top papers > Final answers. Each result will show its citation counts, DOI, and a full-text link to Semantic Scholar website for more information such as background citations, methods citation, related papers and more. - List of Concepts search - e.g. adult learning motivation . The results will present a list the related concepts. - Extract data from a pdf file - Upload a paper and let Elicit extract data for you.
• Export Results - Various ways to export results.
• How to Cite - Includes the elicit.org URL in the citation, for example: Ought; Elicit: The AI Research Assistant; https://elicit.org; accessed xxxx/xx/xx

CONSENSUS.APP

ACADEMIC SEARCH ENGINE- using AI to find insights in research papers.

"We are a search engine that is designed to accept research questions, find relevant answers within research papers, and synthesize the results using the same language model technology." <https://consensus.app/home/blog/maximize-your-consensus-experience-with-these-best-practices/>

• Example - Does the death penalty reduce the crime?   /  Fish oil and depression  /    (1) Extracted & aggregated findings from relevant papers. (2) Results may include AIMS, DESIGN, PARTICIPANTS, FINDINGS or other methodological or report components. (3) Summaries and Full Text
• How to Search Direct questions - Does the death penalty reduce the crime? Relationship between two concepts - Fish oil and depression / Does X cause Y? Open-ended concepts - effects of immigration on local economics Tips and search examples from Consensus' Best Practice   
• Synthesize (beta) / Consensus Meter When the AI recognizes certain types of research questions, this functionality may be activated. It will examine a selection of some studies and provide a summary along with a Consensus Meter illustrating their collective agreement. Try this search: Is white rice linked to diabetes? The Consensus Meter reveals the following outcomes after analyzing 10 papers: 70% indicate a positive association, 20% suggest a possible connection, and 10% indicate no link.

Prompt “ write me a paragraph about the impact of climate change on GDP with citations “

CITATIONS IN CONTEXT

Integrated with Research Solutions.

Over 1.2 billion Citation Statements and metadata from over 181 million papers suggested reference.

How does it work? - "scite uses access to full-text articles and its deep learning model to tell you, for a given publication: - how many times it was cited by others - how it was cited by others by displaying the text where the citation happened from each citing paper - whether each citation offers supporting or contrasting evidence of the cited claims in the publication of interest, or simply mention it."   <https://help.scite.ai/en-us/article/what-is-scite-1widqmr/>

EXAMPLE of seeing all citations and citation statements in one place

More information: Scite: A smart citation index that displays the context of citations and classifies their intent using deep learning  

• GPT3.5 by OpenAI. Knowledge cutoff date is September 2021.
• Input/ Output length - ChatGPT-3.5 allows a maximum token limit of 4096 tokens. According to ChatGPT " On average, a token in English is roughly equivalent to 4 bytes or characters. English words are typically around 5 characters long. This means that, very roughly, you could fit around 800 to 1000 English words within 4096 tokens." 
• According to ChatGPT, the generated responses are non-deterministic by default. So if you run the searches again and get slightly or very different results, it's likely due to this factor.
• ChatGPT may find non-existent references.
• According to this study < https://arxiv.org/ftp/arxiv/papers/2304/2304.06794.pdf > "ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts" within the field of environmental science.  
• Example - "INTERVIEW WITH CHATGPT" as a Research Method & Teaching Tool Some researchers began to use this approach to obtain their research data. Try this Google Scholar search link "interview with ChatGPT"   or see two articles below: (1) Chatting about ChatGPT: how may AI and GPT impact academia and libraries? BD Lund, T Wang - Library Hi Tech News, 2023 (2) An interview with ChatGPT: discussing artificial intelligence in teaching, research, and practice , G Scaringi, M Loche - 2023  

Increased risk of sudden infant death syndrome (SIDS) Increased risk of premature birth Increased risk of low birth weight Increased risk of respiratory problems in newborns Increased risk of respiratory problems in infants exposed to secondhand smoke Increased risk of developing asthma and other respiratory illnesses later in life for infants exposed to secondhand smoke [Note : ChatGPT may generate non-existent references or false knowledge. To find out why Large Language Models hallucinate, check out this Wiki article: Hallucination (artificial intelligence) and this blog post -   A Gentle Introduction to Hallucinations in Large Language Models by Adrian Tam ]

Infant death Neonatal mortality (referring specifically to deaths within the first 28 days of life) Perinatal mortality (referring to deaths occurring during the period from 22 completed weeks of gestation to 7 completed days after birth) Early childhood mortality (referring to deaths occurring within the first five years of life) Child mortality (referring to deaths occurring before the age of 18) [Press the Regenerate button to get more.]

• Example -  RELATED WORDS What are the related words of infant mortality? Neonatal mortality, Post-neonatal mortality, Stillbirths, Low birth weight, Malnutrition, Infectious diseases, Vaccination, Maternal health,  Access to healthcare, Poverty, Social inequality, Sanitation, Hygiene, Water quality, Childbirth complications, Congenital abnormalities, Birth defects, Maternal age, Under-five mortality, Child mortality, Perinatal mortality, Preterm birth, Low birth weight, Sudden infant death syndrome (SIDS), Maternal mortality, Postnatal care, Malnutrition, Immunization, Access to healthcare, Clean water and sanitation, Congenital anomalies, Infant health disparities, Infant mortality rate (IMR), Infant survival.  

(("Infant Death"[Mesh] OR "Sudden Infant Death Syndrome"[Mesh] OR "Infant Mortality"[Mesh] OR "Perinatal Mortality"[Mesh] OR "Neonatal Mortality"[Mesh] OR "Fetal Mortality"[Mesh] OR "Infant Death" OR "Sudden Infant Death Syndrome" OR "Infant Mortality" OR "Perinatal Mortality" OR "Neonatal Mortality" OR "Fetal Mortality") AND ("Risk Factors"[Mesh] OR "Etiology"[Mesh] OR "Prevention and Control"[Mesh] OR "Interventions"[Mesh] OR "Public Health"[Mesh] OR "Health Disparities"[Mesh] OR "Healthcare Disparities"[Mesh] OR "Poverty"[Mesh] OR "Malnutrition"[Mesh] OR "Infection"[Mesh] OR "Congenital Abnormalities"[Mesh] OR "Prematurity"[Mesh] OR "Low Birth Weight"[Mesh] OR "Maternal Education"[Mesh] OR "Maternal Health"[Mesh] OR "Risk Factors" OR "Etiology" OR "Prevention and Control" OR "Interventions" OR "Public Health" OR "Health Disparities" OR "Healthcare Disparities" OR "Poverty" OR "Malnutrition" OR "Infection" OR "Congenital Abnormalities" OR "Prematurity" OR "Low Birth Weight" OR "Maternal Education" OR "Maternal Health")) Comments and Suggestions: #1 -This search string may not work on all database platforms. For example, Medline (OVID) may not be able to run it, Medline & CINAHL (EBSCO) can run it without any problems while PubMed will run it but it will indicate which MeSH terms are not indexed. See PubMed's search History and Details under Advanced . #2 - This is just one possible combination. You may need to adjust it based on your task and the databases you are using . #3 - It might be easier if you break the task into 3 parts: ask for synonyms > ask for thesauri terms > and ask it to combine them.

Examples - DATABASE RECOMMENDATIONS Heath Science - Which databases to use to find articles on the EFFECTS OF MATERNAL SMOKING ON INFANT DEATH? PubMed: This is a database of biomedical literature from the National Library of Medicine. It includes articles from medical journals and other sources on a wide range of health-related topics. Embase: This is a database of biomedical literature that covers more international and pharmaceutical content than PubMed. It includes articles from medical journals and other sources on a wide range of health-related topics. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions, including interventions related to maternal smoking and infant death. Scopus: This is a multidisciplinary database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. Web of Science: This is a database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. CINAHL: This is a database of nursing and allied health literature, including articles on maternal smoking and infant death. [Note: The response above was copied and pasted directly from ChatGPT. No editing was added.] Education -- I am doing a meta-analysis on k-12 STEM education. What databases should I use? ERIC : This is a database of education research and information, including articles from journals, reports, and conference papers. It is a commonly used database for educational research. Education Source : This is a comprehensive database of education research and information, including articles from journals, books, and conference papers. Web of Science: This is a multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. Scopus: This is another multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. PsycINFO: This is a database of psychology research, including articles from journals, books, and dissertations. It can be useful for research on STEM education that includes psychological factors. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions including interventions related to education. [Author's note: You could also ask for the GREY LITERATURE sources related to the topic above,]

Example: ACT-AS-AN-EXPERT PROMPT Here's an alternative way to consolidate all the questions into a single consultation by using this popular Act-As-An-Expert prompt, aka, system message prompt:  I am going to conduct a systematic review on games and mathematics related to K-12 education  I want you to act as a systematic review expert . I will ask you some questions related to my research topic and you advise me on how to do it. 

[You may ask one question at a time] My first question is "which databases should I use?"  My second question is "what are the relevant subject terms, descriptors and key words?" My third question is "how to do data extraction?" ..... , .... Please note that the above prompts are merely for illustrative purposes. Actual questions may contain more specific instructions. As an example, for the first question, could you provide guidance on how to identify relevant publications? Specifically, can you provide a list of the primary databases and grey literature sources related to my topic?  

Example - GREY LITERATURE Please show me all the resources that offer grey literature for conducting research in the field of education     ERIC (Education Resources Information Center): https://eric.ed.gov/     OpenGrey: http://www.opengrey.eu/     British Education Index: https://www.ebscohost.com/academic/british-education-index     WorldCat: https://www.worldcat.org/     ProQuest Dissertations & Theses Global: https://www.proquest.com/products-services/pqdtglobal.html     EThOS (Electronic Theses Online Service): https://ethos.bl.uk/     Institutional Repositories of universities and academic institutions (search for specific institution repositories)     American Educational Research Association (AERA): https://www.aera.net/     National Education Association (NEA): https://www.nea.org/     Association for Supervision and Curriculum Development (ASCD): http://www.ascd.org/     RAND Corporation: https://www.rand.org/     National Center for Education Research (NCER): https://ies.ed.gov/ncer/     National Center for Education Statistics (NCES): https://nces.ed.gov/     European Educational Research Association (EERA): https://www.eera-ecer.de/     UNESCO International Institute for Educational Planning (IIEP): http://www.iiep.unesco.org/     Organization for Economic Cooperation and Development (OECD): https://www.oecd.org/education/     Education Development Center (EDC): https://www.edc.org/     National Institute for Educational Policy Research (NIER) - Japan: https://www.nier.go.jp/     Australian Council for Educational Research (ACER): https://www.acer.org/     Canadian Education Association (CEA): https://www.cea-ace.ca/ My topic is about stem education. Which grey literature databases should I use?    STEM Education Research Centre (SERC) Grey Literature Database    National STEM Education Research Repository (NSERR)    National Science Digital Library (NSDL)    STEM Education Resource Center (SERC) GrayLit Network    STEM Education Grey Literature Library

See other Comparison Examples under Bing AI.

Examples - ZERO SHOT, ONE SHOT & FEW SHOT PROMPTING for literature review See the examples on the left panel- How to Fine Tune Prompts

Bing Chat / Copilot

• Bing Chat has become Copilot.
• CONVERSATIONAL LLM 4.0 + SEARCH ENGINE. Connects to the Internet.
• Three conversation modes: More Creative, More Balanced or More Precise.
• Comparison - Prompt: My topic is about psychology. Which grey literature databases should I use? More Precise - PsycExtra, NIH Library and links to library guides, .gov and .org websites More Balanced - PsycExtra and three main research guides that mention psychology grey literature sources. More Creative- PsycExtra, LILACS, and Worldcat + definition of grey literature + suggestions on searching for professional association websites, newsletters, magazines, standards and guidelines, and other sources that may contain relevant information for your topic.
• Some examples below were tested in Bing Chat only.  
• Example - factors of infant mortality Infant mortality is a term that refers to the death of infants before their first birthday. The leading causes of infant mortality include birth asphyxia, pneumonia, congenital malformations, term birth complications such as abnormal presentation of the fetus umbilical cord prolapse, or prolonged labor, neonatal infection, diarrhea, malaria, measles, and malnutrition1. Many situational factors lead to infant mortality such as the pregnant woman’s level of education, environmental conditions, political infrastructure, and level of medical support1. In the United States, a primary determinant of infant mortality risk is infant birth weight with lower birth weights increasing the risk of infant mortality. The determinants of low birth weight include socioeconomic, psychological, behavioral and environmental factors2.  
• Example: PEER REVIEWED SOURCES I need to find some peer reviewed articles about infant mortality? The answer includes 5 articles. The first one is “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” by Neha Bairoliya and Günther Fink1. A click on  " Tell me more about the first article " leads to this summary: " The first article is titled “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” and was published in PLOS Medicine on March 20, 2018. The authors are Neha Bairoliya and Günther Fink. The study used linked birth and death records for the period 2010–2012 to identify the state- and cause-specific burden of infant mortality among full-term infants (born at 37–42 weeks of gestation) in the United States. The researchers found that the full-term infant mortality rate (FTIMR) was 2.2 per 1,000 live births overall and ranged between 1.29 (Connecticut) and 3.77 (Mississippi) at the state level. Sudden unexpected death in infancy (SUDI) accounted for 43% of FTIM; congenital malformations and perinatal conditions accounted for 31% and 11.3% of FTIM, respectively. The largest mortality differentials between states with good and states with poor FTIMR were found for SUDI, with particularly large risk differentials for deaths due to sudden infant death syndrome (SIDS) and suffocation." More searches: Please find five empirical studies focusing on the factors influencing adult learners engaged in online education. Please locate five scholarly articles on stress management among college students site:pubmed.ncbi.nlm.nih.gov

The ERIC Thesaurus contains nearly 12,000 terms, including more than 4,500 descriptors and 7,000 synonyms1. You can use the term “Academic Achievement” or its synonyms such as “Educational Achievement”, “Student Achievement”, “Academic Performance”, “Academic Success”, “Learning Achievement” and more. [ Note : The follow-up responses include some additional sources. See two below: https://www.powerthesaurus.org/academic_achievement https://eric.ed.gov/?ti=Achievement+Gap   including https://eric.ed.gov/?ti=Academic+Achievement |

My topic is about psychology.  Which grey literature databases should I use?

ChatGPT PsycEXTRA : This database is produced by the American Psychological Association (APA) and includes grey literature such as conference papers, white papers, and government reports. OpenGrey : This database provides access to grey literature produced in Europe, including reports, theses, and conference papers Grey Literature Report : This database is produced by The New York Academy of Medicine and includes reports, conference papers, and other grey literature on health and biomedical topics, including psychology. ProQuest Dissertations and Theses Global : This database provides access to graduate-level research, including theses and dissertations related to psychology. Google Scholar: While not exclusively a grey literature database, Google Scholar can be a useful tool for finding conference papers and other grey literature related to psychology. National Technical Information Service (NTIS) : This database provides access to technical reports produced by U.S. government agencies, including those related to psychology. Bing AI   - [asked in the Precise mode] For psychology, some recommended grey literature databases include PsycEXTRA and PsyArXiv . PsycEXTRA is a database of grey literature material relating to psychology, behavioral sciences and health. PsyArXiv is a psychology archive designed to facilitate rapid dissemination of psychological research. What other models have been developed based on SERVQUAL?

ChatGPT SERVPERF: This is a modified version of SERVQUAL that measures service performance instead of service quality. It was developed by Cronin and Taylor (1992) and is based on the same five dimensions as SERVQUAL. SERVPERF-GAP: This model, developed by Caruana and Ewing (2006), extends the SERVQUAL model to include three additional gaps that can occur when customers evaluate service quality. E-SERVQUAL: This model, developed by Parasuraman et al. (2005), adapts the SERVQUAL scale to measure the quality of online services. SERVCO: This is a modified version of SERVQUAL that includes a sixth dimension, "cost," in addition to the five original dimensions. It was developed by Sureshchandar et al. (2002) to address the importance of cost in service quality evaluation. SERVQ-HC: This is a modified version of SERVQUAL that is specifically designed for evaluating the quality of health care services. It was developed by Cronin et al. (2000) and includes 20 items across five dimensions. Bing AI The Nordic model of service quality2. The hierarchical model of service quality3. The American Customer Satisfaction Index (ACSI)4.

     Bing AI Sidebar - CHAT, THINK, & WRITE

• Examples of Using AI sidebar to Recap Google Scholar findings

Chat - If you highlight a study in the search results of Google Scholar, you will be prompted with a question by AI sidebar asking if you want to send the selected text to it. If you choose to do so, you can then select either  EXPLAIN or EXPAND to learn more about the chosen article. It's worth noting that EXPAND provides more detailed information. You can then click on any of the follow-up links to delve further into the selected article or topic. If the text of the chosen study is written in a foreign language, the AI sidebar can also provide an explanation of the text in English. Another option for extracting the key points from a selected article is to submit the URL of the PDF. Insights - Use the insights button to get more ideas about the topic. Compose - Tell the Edge sidebar your topic and let its Compose tool to generate a draft for you. Google Scholar Button- See also the Plugins and Extension page for how to perform a combined search using Google, Google Scholar, and ChatGPT .

Example: FINDING SIMILAR ARTICLES Find similar articles like this one - [then paste in the abstract ] Note - Use this prompt with Bing chat since real-time web info is required.

Examples: SUMMARIZE + REFERENCE Use a basic prompt like " Please summarize . ..." or add a REFERENCE TEXT that provides the necessary information about what you want it to focus or how the summary or resolution should look like. The reference could be a quote, an excerpt, a partial sentence, a conversation, an abstract, a code snippet and so on. Formula : Specify a role > assign a task > provide a reference text. Example#1 - Scholarly Journal Quote

STEP 1 Prompt: As a research assistant specializing in renewable energy, your task is to locate comparable research studies based on the provided abstract from an article: "This paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and replacement of fossil fuels by various sources of renewable energy."

Bing Chat then found 3 documents: the ScienceDirect paper where the abstract came from and two other documents from un.org and frontiersin.org respectively.

STEP 2 Prompt: Please synthesize the findings of the three studies provided above.

Bing Chat: "Sure! Here is a synthesis of the findings from the three studies:

All three studies emphasize the importance of renewable energy in achieving sustainable development and mitigating climate change. They all discuss various strategies and actions that can be taken to increase the use of renewable energy sources and reduce reliance on fossil fuels.

Henrik Lund’s paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and .....

The United Nations outlines five critical actions the world needs to prioritize now to transform our energy systems and speed up the shift to renewable energy: Make renewable energy technology a global public good, Improve global access to components and raw materials......

“Sustainable Energy Transition for Renewable and Low Carbon Grid” discusses that a sustainable global electricity transition will entail increased use of renewable energy sources particularly wind and solar, nuclear energy as a low carbon energy source, electrification of transport and.......

In summary , these studies suggest that transitioning to renewable energy sources is crucial for sustainable development and mitigating climate change. This can be achieved through various strategies such as increasing energy efficiency, improving access to renewable technology and materials, leveling the playing field for renewables, ending fossil fuel subsidies, and redirecting investments towards renewables." Example #2 Y ou are an expert researcher, given the following article, please discuss its key findings. Reference: How Large Language Models are Transforming Machine-Paraphrased Plagiarism at https://arxiv.org/abs/2210.03568 This is another way to put REFERENCE TEXT. As a side not, role specifying or the use of persona is important as it can impact the level of responses obtained. Just imagine if the designated role were " You are a high school student... ." Example #3 Please read this article and summarize it f or me - "Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making" and then find 5 similar studies and please also summarize each for me.

CONNECTED PAPERS

• RELATED STUDIES
• Uses visual graphs or other ways to show relevant studies. The database is connected to the Semantic Scholar Paper Corpus which has compiled hundreds of millions of published papers across many science and social science fields.
• See more details about how it works .  
• Example - SERVQUAL and then click on SELECT A PAPER TO BUILD THE GRAPH > The first paper was selected. Results: (1) Origin paper - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality + Connected papers with links to Connected Papers / PDF / DOI or Publisher's site / Semantic Scholar / Google Scholar. (2) Graph showing the origin paper + connected papers with links to the major sources . See above. (3) Links to Prior Works and Derivative Works See the detailed citations by Semantic Scholar on the origin SERVQUAL paper on the top of this page within Semantic Scholars.
• How to Search Search by work title. Enter some keywords about a topic.
• Download / Save Download your saved Items in Bib format.

PAPER DIGEST

• SUMMARY & SYNTHESIS
• " Knowledge graph & natural language processing platform tailored for technology domain . <"https://www.paperdigest.org/> Areas covered: technology, biology/health, all sciences areas, business, humanities/ social sciences, patents and grants ...

• LITERATURE REVIEW - https://www.paperdigest.org/review/ Systematic Review - https://www.paperdigest.org/literature-review/
• SEARCH CONSOLE - https://www.paperdigest.org/search/ Conference Digest - NIPS conference papers ... Tech AI Tools: Literature Review  | Literature Search | Question Answering | Text Summarization Expert AI Tools: Org AI | Expert search | Executive Search, Reviewer Search, Patent Lawyer Search...

Daily paper digest / Conference papers digest / Best paper digest / Topic tracking. In Account enter the subject areas interested. Daily Digest will upload studies based on your interests.

RESEARCH RABBIT

• CITATION-BASED MAPPING: SIMILAR / EARLY / LATER WORKS
• " 100s of millions of academic articles and covers more than 90%+ of materials that can be found in major databases used by academic institutions (such as Scopus, Web of Science, and others) ." See its FAQs page. Search algorithms were borrowed from NIH and Semantic Scholar.

The default “Untitled Collection” will collect your search histories, based on which Research Rabbit will send you recommendations for three types of related results: Similar Works / Earlier Works / Later Works, viewable in graph such as Network, Timeline, First Authors etc.

Zotero integration: importing and exporting between these two apps.

• Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality [Login required] Try it to see its Similar Works, Earlier Works and Later Works or other documents.
• Export Results - Findings can be exported in BibTxt, RIS or CSV format.

CITING GENERATIVE AI

• How to cite ChatGPT  [APA] - https://apastyle. apa.org/blog /how-to-cite-chatgpt  
• How to Cite Generative AI  [MLA]  https://style. mla.org /citing-generative-ai/
• Citation Guide - Citing ChatGPT and Other Generative AI (University of Queensland, Australia)
• Next: Dialogues: Insightful Facts >>
• Last Updated: Mar 12, 2024 10:43 AM
• URL: https://tamu.libguides.com/c.php?g=1289555

• Human Editing
• Free AI Essay Writer
• AI Outline Generator
• AI Paragraph Generator
• Paragraph Expander
• Essay Expander
• Literature Review Generator
• Research Paper Generator
• Thesis Generator
• Paraphrasing tool
• AI Rewording Tool
• AI Sentence Rewriter
• AI Rephraser
• AI Paragraph Rewriter
• Summarizing Tool
• AI Content Shortener
• Plagiarism Checker
• AI Detector
• AI Essay Checker
• Citation Generator
• Reference Finder
• Book Citation Generator
• Legal Citation Generator
• Journal Citation Generator
• Reference Citation Generator
• Scientific Citation Generator
• Source Citation Generator
• Website Citation Generator
• URL Citation Generator
• Proofreading Service
• Editing Service
• AI Writing Guides
• AI Detection Guides
• Citation Guides
• Grammar Guides
• Paraphrasing Guides
• Plagiarism Guides
• Summary Writing Guides
• STEM Guides
• Humanities Guides
• Language Learning Guides
• Coding Guides
• Top Lists and Recommendations
• AI Detectors
• AI Writing Services
• Coding Homework Help
• Citation Generators
• Editing Websites
• Essay Writing Websites
• Language Learning Websites
• Math Solvers
• Paraphrasers
• Plagiarism Checkers
• Reference Finders
• Spell Checkers
• Summarizers
• Tutoring Websites

AI Tools For Academic Research: Top 10

The world of academic research is constantly evolving, and artificial intelligence (AI) is playing a significant role in transforming the research landscape. From finding sources to analyzing data, AI-powered tools are making the research process more efficient and accurate. This article provides our roundup of the top 10 AI tools that are revolutionizing academic research .

Reviewing AI Software for Academic Researchers

What’s the toughest part of advancing in your postgraduate studies? For a multitude of students, the challenge lies in tackling the enormous amount of research required. As well as structuring it and putting all observations on paper.

The sheer number of research articles one needs to go through can be intimidating. Additionally, research material tends to be complex, making it difficult to extract the necessary information. This process demands a significant amount of time and effort. Organizing your insights and articulating them in a coherent, insightful, and scholarly manner presents yet another obstacle in postgraduate research.  While AI tools for academic research can help with that issue, the essay writing sites can facilitate the process of finalizing the findings. 

The Choice of The Number 1 AI Tool for Academia: Best Solution

Postdoctoral researcher Mushtaq Bilal believes that ChatGPT will revolutionize academic research, but acknowledges that many academics don’t know how to use it effectively. Academia is split between early AI adopters and those concerned about its impact on academic integrity . Bilal, an early adopter, believes that AI language models can democratize education and promote greater knowledge if used thoughtfully.

Top List of the Academic Research Software

Several experts have raised concerns about the reliability of language models like ChatGPT, noting that their output, when used as a best AI text generator , can sometimes be biased, limited, or inaccurate. However, Bilal argues that being aware of these limitations and adopting the right approach can enable language models to perform valuable work, particularly in academia.

You can ask Consensus about relationships between concepts, or even cause and effect, like whether immigration improves the economy. It’ll give you an answer based on academic research, even listing the papers and summarizing the top ones.

But it’s got a limited scope, though. It only covers six areas: economics, sleep, social policy, medicine, mental health, and health supplements. Still, it seems like a handy resource for those topics.

It saves time by providing quick access to research-backed answers on the covered topics. Consensus bases its answers on academic research, increasing the credibility of the information. The tool provides summaries of the top articles it analyzes, making it easier to understand complex research.

It’s an easily accessible way for users to gain knowledge about specific topics without needing extensive research skills. By providing research-backed answers, Consensus promotes evidence-based thinking.

• Efficient research
• Credible sources
• Encourages evidence-based decision making
• Limited scope
• Potential bias
• AI limitations

Elicit is like a research assistant that uses language models to answer questions, but it’s entirely based on research. This makes it a solid source for having “intelligent conversations” and brainstorming sessions.

What’s cool is that it can find relevant papers even without exact keyword matches, and it can summarize them, making it a handy paper typer that pulls out the key details.

Elicit’s knowledge is solely based on research, which ensures a more reliable and verified source of information. It can find relevant papers without needing perfect keyword matches, making it easier to discover important research.

• Research-based knowledge
• Flexible search
• Supports creative thinking
• Limited to research
• Accessibility

Scite uses AI to provide detailed citation information for research papers, helping researchers evaluate the credibility of their sources. This service is really helpful for getting real citations from actual published papers. It’s great for improving workflows. Scite gives you answers to questions with a detailed list of cited papers. Plus, it tells you the exact number of times a claim has been refuted or corroborated in various journals, making it a powerful tool.

• Accurate citations
• Improves workflow
• Fact-checking capability
• Potential for user error

Research Rabbit

Research Rabbit is a tool for fast-tracking research, and the best part is that it’s free!

It can be called “Spotify of research.” Users can create collections of academic papers that the software can learn from to give them relevant recommendations. Plus, it even visualizes scholarly networks in graphs, so it’s possible follow the work of specific authors or topics.

• Time-saving
• Personalized recommendations
• Limited to academic papers

ChatPDF = “like ChatGPT, but for research papers”. It could be useful for reading and analyzing journal articles.

Basically, you start by uploading a PDF of the research paper into the app, and then you can start asking it questions. ChatPDF will then generate a short summary of the paper and provide examples of questions that it can answer based on the full article.

This could really speed up the process of reading and analyzing research papers, which can be a time-consuming task.

• Summarization capabilities
• Question examples

Perplexity AI

Perplexity AI can potentially become a number 1 tool for academic research. Arguably better than ChatGPT, Perplexity boasts functions that its famous rival doesn’t have. So what exactly is Perplexity AI? 

It’s another AI search engine with powerful academic research abilities. PerplexityAI has access to a variety of different sources, which makes information completely up-to-date. The tool can draw information not only from the Internet, which most other services do well, but also from scholarly sources, WolframAlpha, YouTube, Reddit, news, and Wikipedia. After typing in a search query, a user can specify where exactly they want to receive the information from, and the tool will do the task. Additionally, it can search across individual domains or websites or summarize their content.  

A significant advantage of Perplexity is its advanced functionality when searching for academic materials. Not only does it give you the result, but it also offers a list of related questions and references. This is an edge compared to ChatGPT, especially GPT-3.5, which often makes users question the relevance or even existence of the references it provides.   

With all these features onboard, apps for essay , and Chrome extension, Perplexity is an excellent AI tool for academic research.

• Actual scholar references
• Available for iPhone (Android app is coming)
• Many credible sources of data
• Clunky functionality with PDFs
• Lacks AI conversational skills

Semantic Scholar

Semantic Scholar is an academic search engine driven by artificial intelligence that enables users to filter through millions of scholarly pieces for educationally appropriate content related to their research subject. It integrates artificial intelligence, machine learning, and language processing with semantic analysis to provide users with precise search outcomes.

Using machine learning methodologies, Semantic Scholar deciphers significance and discovers links within academic papers. It then presents these findings, facilitating scholars in rapidly acquiring a comprehensive understanding.

• Highlights the most crucial elements of a paper
• Free to use
• The limited scope of fields for research
• Narrow evaluation metrics of scholarly articles
• Does not search for material behind a paywall

Iris.ai is an artificial intelligence tool designed to aid researchers in scientific discoveries. The service uses natural language processing and machine learning algorithms to comprehend the context of a research project and suggest pertinent literature. It helps navigate and find data sources without relying on specific keywords, making it significantly more efficient than traditional search engines.

Content-based search, context and data filtering, and extracting and systematizing data are just a few of the many other functions of this versatile research tool.  

• Fast and easy to use
• Has access to vast databases of research articles, including open access papers
• Dependent on the accuracy and quality of the AI algorithms
• Not the best choice for marketing research or economics

Paper Digest

Updated August 28, 2023: he service has stopped operations and the website is no longer maintained. Paper Digest is an AI-based academic article summarization service that aims to help researchers quickly grasp the core ideas of a paper without reading the whole thing. It automatically lists out the key sentences of a paper, taking about 10 seconds to do so. It can also reduce reading time to 3 minutes. The service also imitates researcher behavior by automatically summarizing the paper and helping them decide whether it is worth reading. However, Paper Digest may not be suitable for researchers who require more detailed summaries or who need to capture all the nuances of the original paper.

• Can be accessed from any device
• Can be used for free
• Works only with open-access papers
• The summaries may not capture all the nuances of the original paper

SciSpace is an AI-powered platform that aims to modernize scientific research workflows and collaboration. It offers a suite of tools to discover, read, write, collaborate, and publish research papers. It also links users to more than 45,000 verified journal formats that researchers can select from, making it more suitable than Word for research writing. 

SciSpace is a useful service for those looking for an easy and quick way to understand scholar papers. Its AI-powered features and personalized suggestion engine can help researchers stay on track while gaining a comprehensive understanding of the topic. 

• Personalized suggestion engine
• 40,000+ journal templates and processes 30,000+ papers per month
• Has a grammar and spell-checking systems
• Issues with exporting to different journal formats
• The free plan is quite basic and lacks major features

AI-powered tools are transforming the way we approach academic research, making it more efficient, accurate, and accessible. By leveraging the capabilities of these top 10 AI tools, researchers can save time, improve the quality of their work, and contribute to groundbreaking discoveries in their respective fields .

Best Tips How to Make the Most of AI Tools as a PhD student

PhD students employ AI-chatbots, such as ChatGPT, to enhance their studies and boost efficiency. Some ways they use AI-chatbots include:

• Summarizing texts for quicker reading and idea mapping.
• Checking the validity of individual arguments on different aspects.
• Exploring comprehensiveness by discussing generated options and seeking additional possibilities.
• Testing counterfactuals by presenting arguments and asking for opposing viewpoints.
• Preparing for a jury by sharing arguments and requesting ten related questions.
• Requesting critiques on arguments for improvement.

PhD students can also:

• Direct prompts from the perspective of a renowned book on the topic.
• Use ChatGPT as a writing mentor for thesis and research papers.
• Utilize it for basic proofreading of academic texts, adjusting tone and voice as needed, and rating the original text on a scale of 1 to 10.
• Generate an outline of a dissertation’s main chapter using ChatGPT-generated prompts.
• Employ the “freewriting” technique, writing down unfiltered thoughts, then prompting ChatGPT to refine the text for a scientific publication using appropriate language.

Why academichelp.net is a credible source of information:

Stay curious with us. Academichelp.net has been a reliable educational resource since 2011, providing students with the latest news, assignment samples, and other valuable materials. Even with the extensive information we process, our quality remains consistent. Each team member has experience in education, allowing us to evaluate new sector offerings critically. Our reviews are up-to-date and relevant, with impartiality ensured by the A*Help score methodology from mystery shopping. We aren’t affiliated with any listed service providers. Our focus remains on providing our audience with reliable and unbiased data.

What is the best AI academic research tool?

Choosing the best AI platform for academic research depends on your priorities and preferences. Our experience suggests that the top choice is often a website that combines various services in one place. 

Is there a free AI academic research tool?

Yes, there are free AI academic research tools. Many platforms do not require subscriptions or additional payments. Some websites also provide new clients with a free trial to test certain features. Most of these solutions are mentioned in our top list, so be sure to check it out to find the AI service that suits you best.

Which AI model supports academic research?

Academic research is primarily facilitated by language models that use NLP (natural language processing) and deep learning to gather relevant data and generate different types of content. One of the major companies developing language models is OpenAI, with its latest releases including GPT-3, GPT-3.5, and GPT-4 AI. Other popular language models are LamDa, used by Google, and LLaMA, adopted by Meta and its social media companies.

What is the best free AI for academic research?

To identify the best free AI-powered platform for academic research, you need to determine your specific needs, such as text generation, reference finder, rephrasing tool, or other services.

Students also ask

Can ai be used for research.

Absolutely! AI is a valuable tool for research, aiding in data analysis, pattern recognition, and simulations. So, when you feel a little stuck when doing research for your assignments, you can try out an AI helper.

Which AI is best for research?

The ideal AI for research purposes depends on the specific field’s needs and goals! Different AI models excel in various tasks, so there is no definitive answer to that question unless you do a bit of research first.

How is AI used in scientific research?

AI is very often used in scientific research for a number of reasons. It can easily analyze vast datasets, simulate different experiments, and assist the person, helping researchers uncover new insights and continue their work.

Is there an AI that can read scientific papers?

Yes, there are AI systems capable of doing so. They can extract the necessary information from scientific papers according to the prompt you give the system.

What is the smartest AI today?

Determining the smartest AI is subjective since it can be used for a variety of needs. However, models like GPT-3 and GPT-4 have demonstrated remarkable language processing and comprehension abilities, which can significantly ease the process of writing or compiling information.

Can AI discover new knowledge?

AI plays a crucial role in discovering new knowledge by identifying correlations, suggesting hypotheses, and aiding in data analysis. It helps researchers to make certain discoveries. Although AI is getting more and more popular each day, it cannot replace humans and should rather be used as a tool.

Is AI going to replace scientists?

AI is not poised to replace scientists, writers, or anyone for that matter. Instead, it enhances their capabilities, enabling more efficient and effective research, which leads to accelerated progress. Human impact is undeniably necessary when working with AI, even though it may seem the other way.

Can AI discover new things?

Certainly! AI sometimes can discover new things by analyzing data and detecting patterns. This way AI is contributing to scientific advancements and expanding our understanding of the world.

Useful AI solution articles

• Khanmigo: Khan Academy’s AI Solution to Enhance Learning and Tackle Classroom Challenges
• Doctrina AI: Artificial Intelligence for Learning
• Introducing Wisdolia: The AI-Powered Flashcard Generator
• StudyWand: An AI-Powered Tool for Exam Preparation

AI trends and latest news

• Malaysia’s Ministry of Higher Education Developing Guidelines for ChatGPT Usage in Universities
• OpenAI Expert, Anna Bernstein, Shares Tips for Crafting Effective AI Chatbot Prompts

Follow us on Reddit for more insights and updates.

Comments (1)

Welcome to A*Help comments!

We’re all about debate and discussion at A*Help.

We value the diverse opinions of users, so you may find points of view that you don’t agree with. And that’s cool. However, there are certain things we’re not OK with: attempts to manipulate our data in any way, for example, or the posting of discriminative, offensive, hateful, or disparaging material.

Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

What’s the guarantee that inputs provided is not being snooped by someone at the backend? In other words,

Remember Me

Is English your native language ? Yes No

What is your profession ? Student Teacher Writer Other

Forgotten Password?

Username or Email

Tackling the most challenging problems in computer science

Our teams aspire to make discoveries that positively impact society. Core to our approach is sharing our research and tools to fuel progress in the field, to help more people more quickly. We regularly publish in academic journals, release projects as open source, and apply research to Google products to benefit users at scale.

Featured research developments

Mitigating aviation’s climate impact with Project Contrails

Consensus and subjectivity of skin tone annotation for ML fairness

A toolkit for transparency in AI dataset documentation

Building better pangenomes to improve the equity of genomics

A set of methods, best practices, and examples for designing with AI

Learn more from our research

Researchers across Google are innovating across many domains. We challenge conventions and reimagine technology so that everyone can benefit.

Publications

Google publishes over 1,000 papers annually. Publishing our work enables us to collaborate and share ideas with, as well as learn from, the broader scientific community.

Research areas

From conducting fundamental research to influencing product development, our research teams have the opportunity to impact technology used by billions of people every day.

Tools and datasets

We make tools and datasets available to the broader research community with the goal of building a more collaborative ecosystem.

Meet the people behind our innovations

Our teams collaborate with the research and academic communities across the world

Find academic sources for your next paper

Finish Your Research in Minutes. Save Your Sleep.

Paste your essay to find, summarize, and add credible sources. (That's something Google Scholar can't do!)

200m+ research papers

Precise search filters

Just paste your essay

Join 10,000+ students saving 100s of hours

See Sourcely in action 👇

Please wait. This may take a minute... 

If it takes longer than a minute, try again.

Text exceeds 300 characters. Click here to upgrade to SourcelyPRO for unlimited characters

Success: Scroll Down to see results

Publications From

Minimum Citations

Include Keywords

Exclude Keywords

Results for...

Publication Year:

Publication Venue:

Edit your papers with Yomu AI

Seamless Transition from Sources to Masterpiece

Congratulations on finding the perfect sources for your academic paper! Now, take the next step towards crafting a flawless masterpiece with Yomu. Our AI writing assistant is your guide to refined, error-free writing. Edit your paper like a pro with real-time feedback and efficient writing tools. From research to writing, Yomu & Sourcely are your all-in-one solution for academic excellence.

Sources about

Discover more sources for your essay today, sources about .

Trusted By Academics From

Why trust us? Because we are trusted by the absolute best academic institutions, including Harvard, MIT, and Stanford, among others

POWERFUL FEATURES  

Fed up with scrolling through pages of search results? Our source-finding tool simplifies the process so you can find your sources quickly and easily.

Paste Your Essay

Simply paste your essay or paragraph and let Sourcely do the rest! 

Get Credible Summaries

Save time and effort by quickly getting a general overview/summary of a source material

Export References

Save time and ensure accuracy by exporting your sourced references in various formats, making citation and bibliography creation a breeze.

F ind Sources

Hit the button, and watch Sourcely find all suitable sources. 

Free PDF Downloads

Sourcely also allows users to download free PDFs of many of the sources it lists.

Advanced Filters

Tailor your source discovery by applying advanced filters, such as publication year, authorship, relevance, and more.

PRICING & PLANS  

Sourcely is an investment in your academic career, but we know that budgets can be tight. That's why we strive to keep wallet-friendly prices, with monthly plans starting at just $9 per month or yearly plans at $87 - affordable for everyone.

Pay Per Use

Sourcelyfree.

• Skip hours of Manual Research!
• Assured Credibility of Sources
• Only UP TO 300 characters :(
• Quality results for 300 characters

SourcelyPRO Monthly

• Quick and Easy Source-finding
• Ease of Pasting your Entire Essay
• Skip Tedious Manual Research!
• Generate Credible Summaries
• PDF Downloads of Sources
• Search Millions of Sources
• Filter by Year of Publication

SourcelyPRO Yearly

• All features of the Monthly plan
• Save 20% Off the Monthly Plan
• One purchase, endless benefits
• Lock it in before price increases!
• Pro Yearly users suggest features
• Equal to $7.25/month

SourcelyPRO 2000 Words

• Skip tedious Manual Research!
• Total of 2,000 words

Trusted by researchers and organizations around the world

Over 10,000 students, researchers, and industry experts use Sourcely

See what they're saying

10,000 students helped

100,000 hours saved

 250,000 sources generated 

• How does it work? Our AI algorithms analyze the text and identify key themes and concepts. Then, it searches through our vast data set to find relevant and reliable sources to support those themes. This makes it easy for you to find the information you need to back up your work.
• Who can use it? Our service is perfect for students, researchers, writers, and anyone else who needs to find reliable sources to support their work. It's a great tool for anyone looking to improve the credibility and quality of their writing.
• How much does it cost? We offer a variety of pricing options to fit your needs. We have a free basic plan that is very limited and for the full experience, we have paid versions. Our monthly plan is £4.99 a month, our yearly plan is £29.99/year.
• What makes this service different from others? Unlike other services that simply provide a list of sources, our AI is able to understand the context of your text and find sources that are truly relevant and reliable. Additionally, our data set is the largest in the world, giving you access to more information than any other service.
• Is it easy to use? Yes, our service is very user-friendly. Simply upload your text, and our AI will take care of the rest. You can then easily sort and filter through the sources it finds to find the information you need.
• How quickly can I expect to get the result? Our service is instant, you will get the result as soon as you upload the text.
• How accurate is the service? Our AI is constantly being trained and refined to ensure the highest level of accuracy. We are always working to improve our algorithms to provide you with the most relevant and reliable sources possible. ​
• Can I use it for any language? Currently, our service supports English language only.
• Is there a customer support? Yes, we have a dedicated customer support team that is available to help you with any questions or issues you may have. You can contact us via email or chat.

Elman Mansimov

Armin Hamrah

Daniel Felix

Software Developer

Welcome to Sourcely! Our AI-powered source finding tool is built by students for students, and this approach allows us to create a tool that truly understands the needs of the academic community. Our student perspective also enables us to stay up-to-date with the latest research and trends, and our collaborative approach ensures that our tool is continually improving and evolving.

AI tool searches thousands of scientific papers to guide researchers to coronavirus insights

Post Doctoral Fellow, University of California, Berkeley

Graduate Student Researcher, Persson Group, University of California, Berkeley

Disclosure statement

Amalie Trewartha receives funding from the Department of Energy and has previously received funding from the Toyota Research Institute.

John Dagdelen works for Lawrence Berkeley National Laboratory. He receives funding from Berkeley Lab and previously from the Toyota Research Institute.

View all partners

The Research Brief is a short take about interesting academic work.

The big idea

The scientific community worldwide has mobilized with unprecedented speed to tackle the COVID-19 pandemic, and the emerging research output is staggering. Every day, hundreds of scientific papers about COVID-19 come out , in both traditional journals and non-peer-reviewed preprints. There’s already far more than any human could possibly keep up with, and more research is constantly emerging.

And it’s not just new research. We estimate that there are as many as 500,000 papers relevant to COVID-19 that were published before the outbreak, including papers related to the outbreaks of SARS in 2002 and MERS in 2012. Any one of these might contain the key information that leads to effective treatment or a vaccine for COVID-19.

Traditional methods of searching through the research literature just don’t cut it anymore. This is why we and our colleagues at Lawrence Berkeley National Lab are using the latest artificial intelligence techniques to build COVIDScholar , a search engine dedicated to COVID-19. COVIDScholar includes tools that pick up subtle clues like similar drugs or research methodologies to recommend relevant research to scientists. AI can’t replace scientists, but it can help them gain new insights from more papers than they could read in a lifetime.

Why it matters

When it comes to finding effective treatments for COVID-19, time is of the essence. Scientists spend 23% of their time searching for and reading papers . Every second our search tools can save them is more time to spend making discoveries in the lab and analyzing data.

AI can do more than just save scientists time. Our group’s previous work showed that AI can capture latent scientific knowledge from text, making connections that humans missed. There, we showed that AI was able to suggest new, cutting-edge functional materials years before their discovery by humans. The information was there all along, but it took combining information from hundreds of thousands of papers to find it.

We are now applying the same techniques to COVID-19, to find existing drugs that could be repurposed, genetic links that might help develop a vaccine or effective treatment regimens. We’re also starting to build in new innovations, like using molecular structures to help find which drugs are similar to each other, including those that are similar in unexpected ways.

How we do this work

The most important part of our work is the data. We’ve built web scrapers that collect new papers as they’re published from a wide variety of sources, making them available on our website within 15 minutes of their appearance online. We also clean the data, fixing mistakes in formatting and comparing the same paper from multiple sources to find the best version. Our machine learning algorithms then go to work on the paper, tagging it with subject categories and marking work important to COVID-19.

We’re also continuously seeking out experts in new areas. Their input and annotation of data is what allows us to train new AI models.

What’s next

So far, we have assembled a collection of over 60,000 papers on COVID-19, and we’re expanding the collection daily. We’ve also built search tools that group research into categories, suggest related research and allow users to find papers that connect different concepts, such as papers that connect a specific drug to the diseases it’s been used to treat in the past. We’re now building AI algorithms that allow researchers to plug search results into quantitative models for studying topics like protein interactions. We’re also starting to dig through the past literature to find hidden gems.

We hope that very soon, researchers using COVIDScholar will start to identify relationships that they might never have imagined, bringing us closer to treatments and a remedy for COVID-19.

[ You’re too busy to read everything. We get it. That’s why we’ve got a weekly newsletter. Sign up for good Sunday reading. ]

• Artificial intelligence (AI)
• Biomedical research
• Coronavirus
• Machine learning
• Scientific inquiry
• Scientific studies
• Research Brief
• Innovation and Invention

Lecturer (Hindi-Urdu)

Initiative Tech Lead, Digital Products COE

Director, Defence and Security

Opportunities with the new CIEHF

School of Social Sciences – Public Policy and International Relations opportunities

AI Research Tools

Genei is a research tool that automates the process of summarizing background reading and can also generate blogs, articles, and reports. It allows you to

Ai Summary Generator

Ai Summary Generator is a text summarization tool that can instantly summarize lengthy texts or turn them into bullet point lists. It uses AI to

Avidnote is an AI-powered research tool that helps you organize, write, and analyze your academic work more efficiently. With this tool, you can easily upload

Lumina Chat

Lumina Chat is an AI-powered search engine that lets you instantly get detailed answers from over 1 million journal articles and research papers. It allows

ChatPDF allows you to talk to your PDF documents as if they were human. It’s perfect for quickly extracting information or answering questions from large

scite is an AI-powered research tool that helps researchers discover and evaluate scientific articles. It analyzes millions of citations and shows how each article has

Qonqur is an innovative software that allows you to control your computer and digital content using hand gestures, without the need for expensive virtual reality

Consensus is an AI-powered search engine that helps you find evidence-based answers to your research questions. It intelligently searches through over 200 million scientific papers

SciSpace is an AI research assistant that simplifies researching papers through AI-generated explanations and a network showing connections between relevant papers. It aims to automate

WhiteBridge.ai

WhiteBridge is an AI-powered research platform that consolidates data from over 100 public sources to provide you with comprehensive background information on individuals. You can

Samwell AI is an AI writing assistant that’s specifically designed to help students and academics effortlessly write essays, research papers, and other academic content. Its

GigaBrain is a resourceful search engine that uses AI to scan billions of comments across Reddit and other online communities to find the most useful

Discover the latest AI research tools to accelerate your studies and academic research. Search through millions of research papers, summarize articles, view citations, and more.

• Privacy Policy
• Terms & Conditions

Copyright © 2024 EasyWithAI.com

Top AI Tools

• Best Free AI Image Generators
• Best AI Video Editors
• Best AI Meeting Assistants
• Best AI Tools for Students
• Top 5 Free AI Text Generators
• Top 5 AI Image Upscalers

Readers like you help support Easy With AI. When you make a purchase using links on our site, we may earn an affiliate commission at no extra cost to you.

Subscribe to our weekly newsletter for the latest AI tools !

We don’t spam! Read our privacy policy for more info.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Please check your inbox or spam folder to confirm your subscription. Thank you!

University Libraries      University of Nevada, Reno

• Skill Guides
• Subject Guides

Generative AI for Research: AI Research Tools

• Writing Prompts
• AI & Source Evaluation
• AI Research Tools
• AI & Copyright

AI Tools for Finding, Tracking, and Summarizing Research Literature

Many of the tools below can be used in research to assist with finding, tracking, and summarizing sources. These tools are either free or offer free versions that allow users to access a certain number of searches, summaries, or other features on a monthly or other basis.

• Bing Chat Provides responses to questions that contain web references. The search option can be used along with chat to ask questions about the content in individual webpages. For use in the Edge browser.
• Connected Papers Starting with a "seed paper," users can create graphs and lists of articles based on citations in order to visualize topical connections and identify seminal papers. Sources come from the Semantic Scholar database.
• Consensus Provides answers to questions using information drawn from research papers, with associated article summaries, snapshots of articles, and citation help. Sources come from the Semantic Scholar database.
• Elicit Provides answers to questions using information synthesized from scholarly sources, in addition to article summaries. Also allows users to upload and dissect article PDFs. Sources come from the Semantic Scholar database.
• Explainpaper Allows users to upload an article PDF, highlight a passage, and receive an explanation in simpler language along with related web resources. Users can also ask follow-up questions regarding the passage.
• Paper Digest Provides users with lists of sources and summaries in response to a search. Users can also use the Text Rewriter to wikify, paraphrase, questionfy, or summarize a passage.
• Perplexity Acting like a cross between ChatGPT and Google, it returns narrative answers to a query with cited web sources. It also allows users to ask follow-up questions.
• Research Rabbit Starting with a "seed paper," users can explore and visualize connections among papers/authors. Sources come from Semantic Scholar and PubMed.
• Semantic Scholar A free, AI-powered academic search engine with more than 200 million papers covering all disciplines. Allows users to search for research papers, save them to a library, read TLDR (Too Long; Didn't Read) summaries, ask questions of research papers, cite them, find related papers, see citation counts, and set up content alerts.
• << Previous: AI & Source Evaluation
• Next: AI & Copyright >>

Do hours worth of reading in minutes

Try asking or searching for:

Popular papers to read

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Attention is All you Need

mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Deformable DETR: Deformable Transformers for End-to-End Object Detection

How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

Machine Learning

Support-Vector Networks

Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers

Learning Deep Architectures for AI

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

An Introduction to Support Vector Machines

Model-agnostic meta-learning for fast adaptation of deep networks

Semi-supervised learning using Gaussian fields and harmonic functions

Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

Support vector machine learning for interdependent and structured output spaces

A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data

Natural Language

Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference

Learning Transferable Visual Models From Natural Language Supervision

Unified Pre-training for Program Understanding and Generation

Semantic memory: A review of methods, models, and current challenges

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios.

Foundations of Statistical Natural Language Processing

A framework for representing knowledge

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognitio

Semantic similarity in a taxonomy: an information-based measure and its application to problems of ambiguity in natural language

Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks

Top papers of 2023

Top papers of 2022, trending questions, how can increase in nitric oxide increase blood oxygen saturation, what factors influence the effectiveness of virtual reality medical simulations in enhancing learners' empathy, what are the potential challenges and limitations associated with using recombinant mycobacterium for multiple antigen targeted cancer immunotherapy, what evidence-based interventions have been successful in improving motivation among students at risk of academic failure, what is the parental nutrition recommendation for patient with liver dysfunction, limitations of the technology acceptance model in education, is there an ensemble classifier that uses neural network, random forest and logistic regression, how should a female plan workouts and food intake throughout the day, how much people suffering from cancer now days, what are the most effective study techniques for retention and comprehension of information, what is the history behind the concept of goldberg central tessellations, how does the implementation of a specialized science curriculum in junior high school affect students' academic performance, what are critical programmes logic and objective, how does autonomic nervous system control the heart at rest, what is the cost of ultrasound in kenya, why are young adults living at home longer, how do simulation tools impact the effectiveness of research and development in various industries, what are the specific characteristics of the incel culture in south africa, what are the cognitive processes involved in developing higher order thinking skills, what is thermal evaporation process for the synthesis of nanoparticles, how big is the sun, what are the key skills and abilities required for an assertive diagnosis in identifying problems, what is aspirin lipophilicity value 1 to 2, how do simulation tools contribute to the advancement of energy research and development, do fibroadipogenic progenitors express cd133 in human skeletal muscle in disease, what are the challenges of sustainability in maritime museums, what are the general patient safety concerns in the world, how effective are antioxidant creams containing these ingredients in protecting the skin from oxidative stress and damage, what barriers does kenya’s hospitality industry face in adopting ai, what are secondary electron images, what are the issues of an interpreter, what contribute to the number of errors in pleasant being less than unpleasant condition in the emotional stroop experiment, what are the global trends in the use of biological control agents, how do ferric chloride test yiels a blackish positive result, is biofouling an offshore floating wind challenge, what are the most effective surgical interventions for piriform sinus stenosis in newborns, how does the clock-gated ripple carry adder design differ when using different cmos technologies, how is ferrjc chloride test forms a blackish precipitate with hydrolysable tannins, group factors influencing study ability, how does social media shape identity construction, how do cultural and societal factors influence public emotions towards serial killers, what are the challenges of iot technology, is act2 in arabidopsis expressed in the shoot apical meristem, do fibroadipogenic progenitors express fibroblast activating protein in human skeletal muscle, what does heinz voderberg, who intriduced spiral tiling, done, how did paulo freire view the purpose of education, how virtual entertainment affects social media trends and influences fashion trends in the uk market, gsdmb affects asthma, what are the coping mechanisms' employed by women suffering from endometriosis, how ott and pop culture affects social media trends and influences fashion trends in the uk market, to what extent can cultural codes be varied and used for the purpose of nationalism, how does the presence of inorganic carbon in soil affect soil health and fertility, what emotions doe public hold for serial killers, what factors contribute to the success of the al ain football club in the uae, what is milk proteins, what are the specific budgetary constraints that hinder the implementation of integrated marketing communication (imc) strategies in organizations, the epidemiology of open fractures in adults, impact of family on municipal waste generation, what are third variables in correlational research, what is research on neo dft and quantum tunneling, which parts of arabidopsis is act2 expressed, what are the uses of irrigation systems, what emotions do young adults hold for serial killers, how does an integrative neurology approach impact seizure frequency reduction and psychological well-being improvement in patients with epilepsy, what is the role of uv radiation for plants, how do shallow water equations check wind and storm levels, what is the molecular enviroment in early stage melanoma, what are the long-term effects of low self-esteem on mental health and well-being in students, how can therapeutic alliance improve patient adherence to physiotherapy, what are some common misconceptions about snakes that are perpetuated by social media content, what is meant by substance and accidence, how halotolerance and holophily work on organism to adapt vary salinity levels, what were the training evaluation methods used before kirkpatrick's model, can moringa oleifera leaves be used as an eco-friendly alternative to commercial rust removers, what mathematical skills needed in solving real world situation in the philippines, what are the key requirements for compliance with api 5a3 standard, why ceaserian section increase in tanzania, what is expiremental research, what arethe moitives for sharenting among parents, how effective are current interventions in improving sleep quality for firefighters, what is the best treatment of household insects, what are the most debating topics around vitreoretinal lymphoma and intraocluar lymphoma, what are the potential benefits and challenges for multinational enterprises when engaging in international trade negotiations and agreements, what are the key components of a high voltage hvdc substation used in offshore wind farms, how does the use of documentary films contribute to increasing public awareness of mental health issues, how do mobile apps impact the filipino language and culture, what are some protein structures that were determined via nmr, x-ray crystallography, and cryo-em, how do families with low income able to meet basic needs in the philippines, how awareness campaigns on e-government servicesbridge digital divide, function of iron in plants, does reading skills have a significant impact on academic performance among students, what is the effectiveness of an intervention for struggling readers program using egra rrl, are there many rare vertebrate species in the tropics, what are the specific ingredients in ultra-processed foods that contribute to an increased risk of chronic diseases, what are the career opportunities for tvl cookery, how to measure ethics, what are the key bio-political issues facing india during and after the emergency, what is the role of stat6 in regulating macrophage polarization, what is the role of management in implementing an error code system, how does nutrient toxicity affect the lettuce plant in hydroponics, 🔬 researchers worldwide are simplifying papers.

Millions of researchers are already using SciSpace on research papers. Join them and start using your AI research assistant wherever you're reading online.

Mushtaq Bilal, PhD

Researcher @ Syddansk Universitet

SciSpace is an incredible (AI-powered) tool to help you understand research papers better. It can explain and elaborate most academic texts in simple words.

Olesia Nikulina

PhD Candidate

Academic research gets easier day by day. All thanks to AI tools like @scispace Copilot, Copilot can instantly answer your questions and simply explain scientific concepts as you read

Richard Gao

Co-founder evoke-app.com

This is perfect for a layman to scientific information like me. Especially with so much misinformation floating around nowadays, this is great for understanding studies or research others may have misrepresented on purpose or by accident.

Product Hunt

I absolutely adore this product. It's been years since I was in a lab but, I plugged in a study I did way back when and this gets everything right. Equations, hypotheses, and methodologies will be game changers for graduate studies (the current education system severely limits comprehension while encouraging interconnectivity between streams). But, early learners would be able to discover so many papers through this as well. In short, love it

Livia Burbulea

I'm gonna recommend SciSpace to all of my friends and family that are still studying. And I'll definitely love to give it a try for myself, cause you know, education should never stop when you finish your studies. 😀

Sara Botticelli

Product Hunt User.

Wonderful idea! I know this will be used and appreciated by a lot of students, researchers, and lovers of knowledge. Great job, team @saikiranchandha and @shanukumr!

Divyansh Verma

SVNIT'25 Chemical Engineering

SciSpace, is a website where you can easily conduct research. Its most notable feature, in my opinion, is the presence of a #ai-powered copilot which can #simplify and explain any text you highlight in the paper you're reading. #citations and related papers are easily accessible with each paper.

Researcher @ VIU

It´s not only the saved time. Reading scientific literature, specially if you are not an expert in the field is a very attention-intensive process. It´s not a task you can maintain for long periods of time. Having them not just smartly summarised but being able to get meaningful answers is a game-changer for a science journalist

Kalyani Korla, PhD

Product Manager • Healthcare

Upload your pdf and highlight the sections you want to understand. It simplifies those complicated sections of the article in a jiffy. It is not rocket science, but it is always welcome if someone explains the big terms in simpler words.

In the media

Best AI Tools To Empower Your Academic Research

Are you using AI tools to enhance your academic research? That means you are taking one step forward in personalizing your learning experience. Today, AI has simplified research processes and learning, making the education process easier for students and scholars. Let’s explore some brilliant AI tools to help your research.

Thanks to all AI tools, they are helping scholars and students to gather better information today. In the time of the internet, there are many articles available, but which one to select is a challenge. As students devote countless hours to better their academic research, AI tools can simplify their work. 

So, to leverage and gain better knowledge for writing, it is essential to automate some of their tedious tasks.  

Here we will learn about the 12 best AI tools that can help you in better academic research. 

Top AI Tools to Empower Your Academic Research

These AI tools will not only help you gather information but will also help you leverage your knowledge of your subjects. 

Let us take a deep dive into the topic.

1. Google Scholar

To get better information on academic research, students and scholars can consider Google Scholar in their topmost favorite list. Through this tool, you can easily stay up-to-date on the latest research papers, scholarly literature, articles, conference papers, and theses. It also allows scholars to find relevant publications and citations easily. 

Most importantly, its simple user-friendly interface makes it a valuable resource and a great tool to use.

Scite is one of the most popular AI-powered academic research tools that improve any academic research in one go. Its own natural language processing and machine learning helps users do better research on scholarly articles and analyze citations. 

Moreover, Scite allows researchers like you to assess the dependability in any particular context of references. It helps in evaluating the quality and impact of the research. It also provides better visualizations and metrics to understand the citation landscape of a particular paper or a topic. If you have missed out on using this tool, try it out today. 

It is one of the most commonly used AI tools for scholars and students, as it helps with grammar and language correction for academic and technical writing. It has 3000+ grammar checks, tone, and style enhancements, which help scholars write better theses and projects without any errors. 

Trinka helps you document scientific findings and allows you to have a more technical tone and style without any difficulty. Therefore, for academic research purposes, Trinka is the most promising tool, as it helps document research papers and white papers in a better way. 

You can consider Elicit as one of the easiest go-to AI tools in the market to process your knowledge. With the help of this tool, you can design and conduct qualitative research. From analyzing the textual data to specifying the key themes, sentiments, and patterns, a researcher can use this tool to automate. 

Also, Elicit can be used to deduce summaries and visualizations for effective data interpretation. For any researcher, Elicit is a gold mine as it helps them gain deeper insights and make informed decisions.

5. Scholarcy

Scholarly is an AI tool that improves academic research by automating the process of reading, summarizing, and extracting information. It can help you recognize figures, tables, and references from the articles and help grasp the main concepts. 

Additionally, this tool has citation extraction features that allow the users to organize and cite the sources used in the research. It also provides the literature review process which enables you to save valuable time and effort. 

Using artificial intelligence and machine learning algorithms, Knewton allows users to deliver personalized educational content. You can tailor the tool for the educational content as per individual needs and learning styles. This is a one-stop and easy pickup tool in the academic learning phase. 

Knewton also allows users to analyze student performance data, strengths, weaknesses, and progress. By leveraging the benefits of AI, Knewton seeks to improve engagement making it one of the best online learning platforms.

7. IBM Watson

IBM Watson has various AI-powered tools for academic research. This tool has its own Watson Discovery and Watson Natural Language Understanding features. Features like data extraction, sentiment analysis, and language processing are in-build into this tool that smoothens the research process. In this way, this tool can help you discover insights from unstructured data.

Tableau is a powerful tool that helps users to analyze data. With its drag-and-drop interface, Tableau helps users easily explore, understand, and identify data, trends, patterns, and outliers. It supports everything from basic charts and graphs to advanced maps, treemaps, and heat maps. 

It is a popular choice for data analysts, businesses, and researchers across industries for its user-friendly interface and robust data visualization capabilities.

9. Semantic Scholar

Semantic Scholar is an AI academic search engine that focuses only on relevant research papers. It is used in computer science, neuroscience, and the biomedical sciences. Also, its natural language processing and machine learning techniques help to analyze the content. 

This tool can help researchers find and navigate relevant literature, visualize citations, and track scholarly articles. It’s advanced search capabilities and citation analysis are some of the most recommended features to use. With its AI-driven approach, you can efficiently create and deliver high-quality scientific literature.

10. Consensus

Consensus is one of the best AI tools if you are looking for genuine scientific findings. Using this AI tool , you can’t go wrong with any research information, as they source the information for you only from published sources. That makes the process very reliable and uncomplicated to understand the subject and document it effectively. 

Also, this AI tool scans each topic thoroughly (through peer-reviewed research) so that it can provide you with a genuine and well-researched article that will reduce your stress. If you haven’t tried it, then you must try it today. 

11. Mendeley

Mendeley is a user-friendly AI tool to organize, share, and cite your research papers properly in one place. It helps you organize your PDFs, create better bibliographies, and annotate documents easily. 

Moreover, this tool enables researchers to collaborate on projects and discover relevant articles based on their interests. Mendeley’s powerful features and integration into academic workflows make it a practical tool. It helps you to streamline your management and enhance collaboration within the scholarly community.

Zotero is an AI-powered management tool and your personal research assistant. It is specially designed to help researchers and scholars collect, organize, annotate, cite, and share research documents. This tool can help you customize all your collections and automatically extract metadata from sources. 

Zotero has 10,000 citation styles for you to format your work and match your style to a publication. Moreover, it takes help from references and bibliographies to edit text and give you genuine information in your Google Doc or Word document. 

In the world of creativity, use AI tools or develop AI apps that will ultimately enhance your learning instead of thinking of them as a threat. Today, AI is the game-changer in every field, as it takes no time to deliver you bundles of information. So, as an academic researcher or scholar, use them to speed up your work and unburden yourself from unnecessary stress. So, you can upskill your knowledge to produce better theses or assignments. 

• : By clicking here, I state that I have read and understood the terms and conditions mentioned above.

To stay updated with AI and its applications in research work and writing papers for publications

Rate this article Cancel Reply

Your email address will not be published.

Recommended from Academy

• AI in Academia
• Thought Leadership
• Trending Now

Authenticating AI-Generated Scholarly Outputs: Practical approaches to take

The rapid advancements in artificial intelligence (AI) have given rise to a new era of…

Simplifying the Literature Review Journey — A comparative analysis of 6 AI summarization tools

Imagine having to skim through and read mountains of research papers and books, only to…

6 Leading AI Detection Tools for Academic Writing — A comparative analysis

The advent of AI content generators, exemplified by advanced models like ChatGPT, Claude AI, and…

• Industry News

Controversy Erupts Over AI-Generated Visuals in Scientific Publications

In recent months, the scientific community has been grappling with a growing trend: the integration…

• Reporting Research

How to Improve Lab Report Writing: Best practices to follow with and without AI-assistance

Imagine you’re a scientist who just made a ground-breaking discovery! You want to share your…

I am looking for Editing/ Proofreading services for my manuscript Tentative date of next journal submission:

What should universities' stance be on AI tools in research and academic writing?

Reference management. Clean and simple.

The top list of academic search engines

1. Google Scholar

4. science.gov, 5. semantic scholar, 6. baidu scholar, get the most out of academic search engines, frequently asked questions about academic search engines, related articles.

Academic search engines have become the number one resource to turn to in order to find research papers and other scholarly sources. While classic academic databases like Web of Science and Scopus are locked behind paywalls, Google Scholar and others can be accessed free of charge. In order to help you get your research done fast, we have compiled the top list of free academic search engines.

Google Scholar is the clear number one when it comes to academic search engines. It's the power of Google searches applied to research papers and patents. It not only lets you find research papers for all academic disciplines for free but also often provides links to full-text PDF files.

• Coverage: approx. 200 million articles
• Abstracts: only a snippet of the abstract is available
• Related articles: ✔
• References: ✔
• Cited by: ✔
• Links to full text: ✔
• Export formats: APA, MLA, Chicago, Harvard, Vancouver, RIS, BibTeX

BASE is hosted at Bielefeld University in Germany. That is also where its name stems from (Bielefeld Academic Search Engine).

• Coverage: approx. 136 million articles (contains duplicates)
• Abstracts: ✔
• Related articles: ✘
• References: ✘
• Cited by: ✘
• Export formats: RIS, BibTeX

CORE is an academic search engine dedicated to open-access research papers. For each search result, a link to the full-text PDF or full-text web page is provided.

• Coverage: approx. 136 million articles
• Links to full text: ✔ (all articles in CORE are open access)
• Export formats: BibTeX

Science.gov is a fantastic resource as it bundles and offers free access to search results from more than 15 U.S. federal agencies. There is no need anymore to query all those resources separately!

• Coverage: approx. 200 million articles and reports
• Links to full text: ✔ (available for some databases)
• Export formats: APA, MLA, RIS, BibTeX (available for some databases)

Semantic Scholar is the new kid on the block. Its mission is to provide more relevant and impactful search results using AI-powered algorithms that find hidden connections and links between research topics.

• Coverage: approx. 40 million articles
• Export formats: APA, MLA, Chicago, BibTeX

Although Baidu Scholar's interface is in Chinese, its index contains research papers in English as well as Chinese.

• Coverage: no detailed statistics available, approx. 100 million articles
• Abstracts: only snippets of the abstract are available
• Export formats: APA, MLA, RIS, BibTeX

RefSeek searches more than one billion documents from academic and organizational websites. Its clean interface makes it especially easy to use for students and new researchers.

• Coverage: no detailed statistics available, approx. 1 billion documents
• Abstracts: only snippets of the article are available
• Export formats: not available

Consider using a reference manager like Paperpile to save, organize, and cite your references. Paperpile integrates with Google Scholar and many popular databases, so you can save references and PDFs directly to your library using the Paperpile buttons:

Google Scholar is an academic search engine, and it is the clear number one when it comes to academic search engines. It's the power of Google searches applied to research papers and patents. It not only let's you find research papers for all academic disciplines for free, but also often provides links to full text PDF file.

Semantic Scholar is a free, AI-powered research tool for scientific literature developed at the Allen Institute for AI. Sematic Scholar was publicly released in 2015 and uses advances in natural language processing to provide summaries for scholarly papers.

BASE , as its name suggest is an academic search engine. It is hosted at Bielefeld University in Germany and that's where it name stems from (Bielefeld Academic Search Engine).

CORE is an academic search engine dedicated to open access research papers. For each search result a link to the full text PDF or full text web page is provided.

Science.gov is a fantastic resource as it bundles and offers free access to search results from more than 15 U.S. federal agencies. There is no need any more to query all those resources separately!

Mobile Navigation

Research index, filter and sort, filter selections, sort options, research papers.

• Computer Vision
• Federated Learning
• Reinforcement Learning
• Natural Language Processing
• New Releases
• AI Dev Tools
• Advisory Board Members
• 🐝 Partnership and Promotion

Niharika Singh

Niharika is a Technical consulting intern at Marktechpost. She is a third year undergraduate, currently pursuing her B.Tech from Indian Institute of Technology(IIT), Kharagpur. She is a highly enthusiastic individual with a keen interest in Machine learning, Data science and AI and an avid reader of the latest developments in these fields.

• Niharika Singh https://www.marktechpost.com/author/niharika98678/ Tired of writing HTML by hand? Meet OpenUI Project: An AI Tool that Lets You Describe UI Using Your Imagination and then See it Rendered Live
• Niharika Singh https://www.marktechpost.com/author/niharika98678/ PromptTools Project: Open-Source Toolkit for Prompt Testing and Experimentation with Support for both LLMs and Vector Databases
• Niharika Singh https://www.marktechpost.com/author/niharika98678/ Meet OpenDevin: An Open-Source Alternative to Devin (an Autonomous AI Software Engineer)
• Niharika Singh https://www.marktechpost.com/author/niharika98678/ Meet Deep-Seek: An Open Source Research Agent Designed as an Internet Scale Retrieval Engine

RELATED ARTICLES MORE FROM AUTHOR

Top python programming books to read in 2024, meet dawn ai: an ai analytics start-up transforming user requests and model outputs into metrics, tired of writing html by hand meet openui project: an ai tool that lets you describe ui using your imagination and then see it..., 10 companies powering fintech with artificial intelligence (ai), this ai paper from arizona state university discusses whether large language models (llms) can reason and plan, openai unveils chatgpt for all: no account, no problem, tired of writing html by hand meet openui project: an ai tool that lets..., meet dawn ai: an ai analytics start-up transforming user requests and model outputs into..., this ai paper from arizona state university discusses whether large language models (llms) can..., from theory to robotics: applying sums-of-squares optimization for better control.

• AI Magazine
• Privacy & TC
• Cookie Policy

🐝 FREE AI Courses on RAG + Deployment of an Healthcare AI App + LangChain Colab Notebook all included

Thank You 🙌

Privacy Overview

Suggestions or feedback?

MIT News | Massachusetts Institute of Technology

• Machine learning
• Social justice
• Black holes
• Classes and programs

Departments

• Aeronautics and Astronautics
• Brain and Cognitive Sciences
• Architecture
• Political Science
• Mechanical Engineering

Centers, Labs, & Programs

• Abdul Latif Jameel Poverty Action Lab (J-PAL)
• Picower Institute for Learning and Memory
• Lincoln Laboratory
• School of Architecture + Planning
• School of Engineering
• School of Humanities, Arts, and Social Sciences
• Sloan School of Management
• School of Science
• MIT Schwarzman College of Computing

Large language models use a surprisingly simple mechanism to retrieve some stored knowledge

Press contact :.

Previous image Next image

Large language models, such as those that power popular artificial intelligence chatbots like ChatGPT, are incredibly complex. Even though these models are being used as tools in many areas, such as customer support, code generation, and language translation, scientists still don’t fully grasp how they work.

In an effort to better understand what is going on under the hood, researchers at MIT and elsewhere studied the mechanisms at work when these enormous machine-learning models retrieve stored knowledge.

They found a surprising result: Large language models (LLMs) often use a very simple linear function to recover and decode stored facts. Moreover, the model uses the same decoding function for similar types of facts. Linear functions, equations with only two variables and no exponents, capture the straightforward, straight-line relationship between two variables.

The researchers showed that, by identifying linear functions for different facts, they can probe the model to see what it knows about new subjects, and where within the model that knowledge is stored.

Using a technique they developed to estimate these simple functions, the researchers found that even when a model answers a prompt incorrectly, it has often stored the correct information. In the future, scientists could use such an approach to find and correct falsehoods inside the model, which could reduce a model’s tendency to sometimes give incorrect or nonsensical answers.

“Even though these models are really complicated, nonlinear functions that are trained on lots of data and are very hard to understand, there are sometimes really simple mechanisms working inside them. This is one instance of that,” says Evan Hernandez, an electrical engineering and computer science (EECS) graduate student and co-lead author of a paper detailing these findings .

Hernandez wrote the paper with co-lead author Arnab Sharma, a computer science graduate student at Northeastern University; his advisor, Jacob Andreas, an associate professor in EECS and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL); senior author David Bau, an assistant professor of computer science at Northeastern; and others at MIT, Harvard University, and the Israeli Institute of Technology. The research will be presented at the International Conference on Learning Representations.

Finding facts

Most large language models, also called transformer models, are neural networks . Loosely based on the human brain, neural networks contain billions of interconnected nodes, or neurons, that are grouped into many layers, and which encode and process data.

Much of the knowledge stored in a transformer can be represented as relations that connect subjects and objects. For instance, “Miles Davis plays the trumpet” is a relation that connects the subject, Miles Davis, to the object, trumpet.

As a transformer gains more knowledge, it stores additional facts about a certain subject across multiple layers. If a user asks about that subject, the model must decode the most relevant fact to respond to the query.

If someone prompts a transformer by saying “Miles Davis plays the. . .” the model should respond with “trumpet” and not “Illinois” (the state where Miles Davis was born).

“Somewhere in the network’s computation, there has to be a mechanism that goes and looks for the fact that Miles Davis plays the trumpet, and then pulls that information out and helps generate the next word. We wanted to understand what that mechanism was,” Hernandez says.

The researchers set up a series of experiments to probe LLMs, and found that, even though they are extremely complex, the models decode relational information using a simple linear function. Each function is specific to the type of fact being retrieved.

For example, the transformer would use one decoding function any time it wants to output the instrument a person plays and a different function each time it wants to output the state where a person was born.

The researchers developed a method to estimate these simple functions, and then computed functions for 47 different relations, such as “capital city of a country” and “lead singer of a band.”

While there could be an infinite number of possible relations, the researchers chose to study this specific subset because they are representative of the kinds of facts that can be written in this way.

They tested each function by changing the subject to see if it could recover the correct object information. For instance, the function for “capital city of a country” should retrieve Oslo if the subject is Norway and London if the subject is England.

Functions retrieved the correct information more than 60 percent of the time, showing that some information in a transformer is encoded and retrieved in this way.

“But not everything is linearly encoded. For some facts, even though the model knows them and will predict text that is consistent with these facts, we can’t find linear functions for them. This suggests that the model is doing something more intricate to store that information,” he says.

Visualizing a model’s knowledge

They also used the functions to determine what a model believes is true about different subjects.

In one experiment, they started with the prompt “Bill Bradley was a” and used the decoding functions for “plays sports” and “attended university” to see if the model knows that Sen. Bradley was a basketball player who attended Princeton.

“We can show that, even though the model may choose to focus on different information when it produces text, it does encode all that information,” Hernandez says.

They used this probing technique to produce what they call an “attribute lens,” a grid that visualizes where specific information about a particular relation is stored within the transformer’s many layers.

Attribute lenses can be generated automatically, providing a streamlined method to help researchers understand more about a model. This visualization tool could enable scientists and engineers to correct stored knowledge and help prevent an AI chatbot from giving false information.

In the future, Hernandez and his collaborators want to better understand what happens in cases where facts are not stored linearly. They would also like to run experiments with larger models, as well as study the precision of linear decoding functions.

“This is an exciting work that reveals a missing piece in our understanding of how large language models recall factual knowledge during inference. Previous work showed that LLMs build information-rich representations of given subjects, from which specific attributes are being extracted during inference. This work shows that the complex nonlinear computation of LLMs for attribute extraction can be well-approximated with a simple linear function,” says Mor Geva Pipek, an assistant professor in the School of Computer Science at Tel Aviv University, who was not involved with this work.

This research was supported, in part, by Open Philanthropy, the Israeli Science Foundation, and an Azrieli Foundation Early Career Faculty Fellowship.

Share this news article on:

Related links.

• Evan Hernandez
• Jacob Andreas
• Language and Intelligence Group
• Computer Science and Artificial Intelligence Laboratory
• Department of Electrical Engineering and Computer Science

Related Topics

• Computer science and technology
• Artificial intelligence
• Human-computer interaction
• Computer Science and Artificial Intelligence Laboratory (CSAIL)
• Electrical Engineering & Computer Science (eecs)

Related Articles

Demystifying machine-learning systems

AI agents help explain other AI systems

3 Questions: Jacob Andreas on large language models

Solving a machine-learning mystery

Previous item Next item

More MIT News

Designing solutions to ensure equity in health care

Read full story →

Training manufacturing technologists to be future shop floor leaders

Characterizing social networks

MIT economics to launch new predoctoral fellowship program

Programming functional fabrics

Does technology help or hurt employment?

• More news on MIT News homepage →

Massachusetts Institute of Technology 77 Massachusetts Avenue, Cambridge, MA, USA

• Map (opens in new window)
• Events (opens in new window)
• People (opens in new window)
• Careers (opens in new window)
• Accessibility
• Social Media Hub
• MIT on Facebook
• MIT on YouTube
• MIT on Instagram

• Artificial Intelligence

Here’s why AI search engines really can’t kill Google

The ai search tools are getting better — but they don’t yet understand what a search engine really is and how we really use them..

By David Pierce , editor-at-large and Vergecast co-host with over a decade of experience covering consumer tech. Previously, at Protocol, The Wall Street Journal, and Wired.

Share this story

AI is coming for the search business. Or so we’re told. As Google seems to keep getting worse, and tools like ChatGPT, Google Gemini, and Microsoft Copilot seem to keep getting better, we appear to be barreling toward a new way to find and consume information online. Companies like Perplexity and You.com are pitching themselves as next-gen search products, and even Google and Bing are making huge bets that AI is the future of search . Bye bye, 10 blue links; hello direct answers to all my weird questions about the world.

But the thing you have to understand about a search engine is that a search engine is many things. For all the people using Google to find important and hard-to-access scientific information, orders of magnitude more are using it to find their email inbox, get to Walmart’s website, or remember who was president before Hoover. And then there’s my favorite fact of all: that a vast number of people every year go to Google and type “google” into the search box. We mostly talk about Google as a research tool, but in reality, it’s asked to do anything and everything you can think of, billions of times a day.

The real question in front of all these would-be Google killers, then, is not how well they can find information. It’s how well they can do everything Google does. So I decided to put some of the best new AI products to the real test: I grabbed the latest list of most-Googled queries and questions according to the SEO research firm Ahrefs and plugged them into various AI tools. In some instances, I found that these language model-based bots are genuinely more useful than a page of Google results. But in most cases, I discovered exactly how hard it will be for anything — AI or otherwise — to replace Google at the center of the web.

People who work in search always say there are basically three types of queries. First and most popular is navigation, which is just people typing the name of a website to get to that website. Virtually all of the top queries on Google, from “youtube” to “wordle” to “yahoo mail,” are navigation queries. In actual reality, this is a search engine’s primary job: to get you to a website.

In actual reality, a search engine’s primary job is to get you to a website

For navigational queries, AI search engines are universally worse than Google. When you do a navigational Google search, it’s exceedingly rare that the first result isn’t the one you’re looking for — sure, it’s odd to show you all those results when what Google should actually do is just take you directly to amazon.com or whatever, but it’s fast and it’s rarely wrong. The AI bots, on the other hand, like to think for a few seconds and then provide a bunch of quasi-useful information about the company when all I want is a link. Some didn’t even link to amazon.com.

I don’t hate the additional information so much as I hate how long these AI tools take to get me what I need. Waiting 10 seconds for three paragraphs of generated text about Home Depot is not the answer; I just want a link to Home Depot. Google wins that race every time.

The next most popular kind of search is the information query: you want to know something specific, about which there is a single right answer. “NFL scores” is a hugely popular information query; “what time is it” is another one; so is “weather.” It doesn’t matter who tells you the score or the time or the temperature, it’s just a thing you need to know.

Here, the results are all over the map. For real-time stuff like sports scores, the AI is not to be trusted: You.com and Perplexity both frequently gave me outdated information, though Copilot usually got it right. Google not only gets it right but usually pops up a widget with other stats and information, which is better than the others. Ditto anything requiring your specific location or context — Google probably has that information about you, but the AI bots mostly don’t.

When it comes to more evergreen information like “how many weeks in a year” or “when is mother’s day,” everything I tested got it right. In many cases I actually preferred the AI answers, which add a bit of helpful context. But I’m not sure how often I can trust them. Google told me there are 52.1429 weeks in a year, but You.com explained that actually it’s 52 weeks and a day, plus an added day on leap years. That’s more useful than just 52.1429! But then Perplexity told me that actually, a common year is 52 weeks, and a leap year is 52 weeks and a day — before directly contradicting itself two sentences later. Here’s the whole answer; just try to make sense of it:

A common year has approximately 52 weeks, while a leap year has 52 weeks and 1 day. In more precise terms, a regular year actually consists of 52.143 weeks, which means there is one additional day in a normal year. On the other hand, a leap year, occurring every four years except for certain exceptions, has 52 weeks and 2 days. This difference in the number of weeks is due to the extra day in a common year and the additional day in February during a leap year.

After doing some more research, I am now confident that the answer is what You.com said. But this all took too long, and forcing me to fact-check my searches kind of defeats the purpose of helpfully summarizing things for me. Google continues to win here on one thing and one thing alone: speed. 

There is one sub-genre of information queries in which the exact opposite is true, though. I call them Buried Information Queries. The best example I can offer is the very popular query, “how to screenshot on mac.” There are a million pages on the internet that contain the answer — it’s just Cmd-Shift-3 to take the whole screen or Cmd-Shift-4 to capture a selection, there, you’re welcome — but that information is usually buried under a lot of ads and SEO crap. All the AI tools I tried, including Google’s own Search Generative Experience, just snatch that information out and give it to you directly. This is great! 

Are there complicated questions inherent in that, which threaten the business model and structure of the web? Yep ! But as a pure searching experience, it’s vastly better. I’ve had similar results asking about ingredient substitutions, coffee ratios, headphone waterproofing ratings, and any other information that is easy to know and yet often too hard to find. 

This brings me to the third kind of Google search: the exploration query. These are questions that don’t have a single answer, that are instead the beginning of a learning process. On the most popular list, things like “how to tie a tie,” “why were chainsaws invented,” and “what is tiktok” count as explorational queries. If you ever Googled the name of a musician you just heard about, or have looked up things like “stuff to do in Helena Montana” or “NASA history,” you’re exploring. These are not, according to the rankings, the primary things people use Google for. But these are the moments AI search engines can shine.

Like, wait: why were chainsaws invented? Copilot gave me a multipart answer about their medical origins, before describing their technological evolution and eventual adoption by lumberjacks. It also gave me eight pretty useful links to read more. Perplexity gave me a much shorter answer, but also included a few cool images of old chainsaws and a link to a YouTube explainer on the subject. Google’s results included a lot of the same links, but did none of the synthesizing for me. Even its generative search only gave me the very basics.

My favorite thing about the AI engines is the citations. Perplexity, You.com, and others are slowly getting better at linking to their sources, often inline, which means that if I come across a particular fact that piques my interest, I can go straight to the source from there. They don’t always offer enough sources, or put them in the right places, but this is a good and helpful trend.

One experience I had while doing these tests was actually the most eye-opening of all. The single most-searched question on Google is a simple one: “what to watch.” Google has a whole specific page design for this, with rows of posters featuring “Top picks” like Dune: Part Two and Imaginary ; “For you” which for me included Deadpool and Halt and Catch Fire ; and then popular titles and genre-sorted options. None of the AI search engines did as well: Copilot listed five popular movies; Perplexity offered a random-seeming smattering of options from Girls5eva to Manhunt to Shogun ; You.com gave me a bunch of out of date information and recommended I watch “the 14 best Netflix original movies” without telling me what they are.

AI is the right idea but a chatbot is the wrong interface

In this case, AI is the right idea — I don’t want a bunch of links, I want an answer to my question — but a chatbot is the wrong interface. For that matter, so is a page of search results! Google, obviously aware that this is the most-asked question on the platform, has been able to design something that works much better.

In a way, that’s a perfect summary of the state of things. At least for some web searches, generative AI could be a better tool than the search tech of decades past. But modern search engines aren’t just pages of links. They’re more like miniature operating systems. They can answer questions directly, they have calculators and converters and flight pickers and all kinds of other tools built right in, they can get you where you’re going with just a click or two. The goal of most search queries, according to these charts, is not to start a journey of information wonder and discovery. The goal is to get a link or an answer, and then get out. Right now, these LLM-based systems are just too slow to compete.

The big question, I think, is less about tech and more about product. Everyone, including Google, believes that AI can help search engines understand questions and process information better. That’s a given in the industry at this point. But can Google reinvent its results pages, its business model, and the way it presents and summarizes and surfaces information, faster than the AI companies can turn their chatbots into more complex, more multifaceted tools? Ten blue links isn’t the answer for search, but neither is an all-purpose text box. Search is everything, and everything is search. It’s going to take a lot more than a chatbot to kill Google.

April Fools’ Day 2024: the best and cringiest pranks

Transparent vice, google agrees to destroy browsing data collected in incognito mode, 20 years of gmail, now you can use chatgpt without an account.

More from Artificial Intelligence

Microsoft’s new era of AI PCs will need a Copilot key, says Intel

Airtable brings AI summarization to paying users

Apple’s WWDC 2024 is set for June 10th

Adobe’s new GenStudio platform is an AI factory for advertisers

Welcome to the MIT CISR website!

This site uses cookies. Review our Privacy Statement.

Scaling AI: Sustaining AI @Scale—Session Presentation

Why can't i view this research.

This presentation from MIT CISR's 2024 European International Executive Forum event is available only to logged-in members and attendees of the event.

See the list of MIT CISR members

Related publications.

Research Briefing

Building ai explanation capability for the ai-powered organization.

Building Advanced Data Monetization Capabilities for the AI-Powered Organization

Working Paper: Vignette

Microsoft’s ai scaling journey for occupancy prediction.

About the Researcher

Barbara H. Wixom, Principal Research Scientist, MIT Center for Information Systems Research (CISR)

Mit center for information systems research (cisr).

Founded in 1974 and grounded in MIT's tradition of combining academic knowledge and practical purpose, MIT CISR helps executives meet the challenge of leading increasingly digital and data-driven organizations. We work directly with digital leaders, executives, and boards to develop our insights. Our consortium forms a global community that comprises more than seventy-five organizations.

MIT CISR Associate Members

MIT CISR wishes to thank all of our associate members for their support and contributions.

MIT CISR's Mission Expand

MIT CISR helps executives meet the challenge of leading increasingly digital and data-driven organizations. We provide insights on how organizations effectively realize value from approaches such as digital business transformation, data monetization, business ecosystems, and the digital workplace. Founded in 1974 and grounded in MIT’s tradition of combining academic knowledge and practical purpose, we work directly with digital leaders, executives, and boards to develop our insights. Our consortium forms a global community that comprises more than seventy-five organizations.

Search Results

• 28 NOVEMBER 2023 · RESEARCH BULLETIN NO. 113

Reports of AI ending human labour may be greatly exaggerated

by Stefania Albanesi , António Dias da Silva , Juan Francisco Jimeno , Ana Lamo and Alena Wabitsch [ 1 ]

Recent advances in artificial intelligence (AI) have revived the debate about the impact of new technologies on jobs (e.g. Frey and Osborne, 2017; Susskind, 2020; and Acemoglu, 2021). Waves of innovation have usually been accompanied by anxiety about the future of jobs. This apprehension persists, even though history suggests that previous fears about labour becoming redundant were exaggerated (e.g. Autor, 2015; Bessen, 2019). In fact, in this article we show that during the deep learning boom of the 2010s, occupations potentially more exposed to AI-enabled technologies actually increased their employment share in Europe. However, the jury is still out on whether the same can be expected from new developments in AI-enabled technologies. When the verdict comes in, it could be win or lose – not only for jobs, but also for equality and prosperity in Europe.

The evidence so far on AI and employment

AI breakthroughs have come in many fields. These include advances in robotics, supervised and unsupervised learning, natural language processing, machine translation and image recognition, to name but a few. AI has applications among masses of other activities that enable automation of human labour in non-routine tasks, both in manufacturing and also in services – from providing medical advice to writing code. AI is thus a general-purpose technology that can automate work in virtually every occupation. It stands in contrast to other technologies such as computerisation and industrial robotics, which only allow a limited set of tasks to be automated by implementing manually specified rules.

The empirical evidence on the effect of AI-enabled technologies on jobs and wages is still evolving. For example, both Felten et al. (2019) and Acemoglu et al. (2022) conclude that occupations more exposed to AI experience no significant impact on employment. However, Acemoglu et al. (2022) also find that AI-exposed establishments reduced non-AI and overall hiring. That would imply that while new tasks are being created, AI is also replacing human labour in a subset of tasks. Moreover, Felten et al. (2019) find that occupations impacted by AI actually experience a small rise in wages. On a different note, Webb (2020) argues that, compared with either software or robots, AI-enabled technologies are likely to have a greater impact on high-skilled workers in particular. Meanwhile, the literature to date focuses mostly on the United States.

New evidence for Europe

In a recent paper (Albanesi et al. 2023), we examine the link between AI-enabled technologies and employment shares in 16 European countries over the period 2011-19 [ 2 ] . These years saw the rise of deep learning applications such as language processing, image recognition, algorithm-based recommendations or fraud detection. Though more limited in scope than the current generative AI models such as ChatGPT, deep learning applications are nonetheless revolutionary – and still trigger concerns about the impact on jobs. We use data at three-digit occupation level (according to the International Standard Classification of Occupations) from Eurostat’s Labour Force Survey, as well as two proxies for potential AI-enabled automation borrowed from the literature. The first proxy is the AI Occupational Impact created by Felten et al. (2018) and Felten et al. (2019), which links advances in specific applications of AI to abilities required for each occupation as described in O*NET [ 3 ] . The second one is a measure of the exposure of tasks and occupations to AI, constructed by Webb (2020) by quantifying the text overlap between AI patent descriptions and job descriptions from O*NET. In addition, we compare the exposure to AI-enabled technologies with exposure to software by using a software exposure measured as constructed by Webb (2020).

These data reveal that around 25% of all jobs in these European countries were in occupations highly exposed to AI-enabled automation – specifically, in the upper third of the exposure measure. The degree of exposure is as much an opportunity as it is a risk. The outcome for jobs depends on whether the AI-enabled technologies will substitute or complement labour. Compared with occupations more exposed to advances in software, those more exposed to AI employ a larger proportion of high-skilled workers (Chart 1). This supports the case that AI-enabled technologies could be in competition with high-skilled jobs. While the exposure to technology varies for different levels of skills, it is relatively uniform across age groups (not shown in the chart).

Exposure to technology by education level

average percentile

Source: Albanesi et al. (2023).

Notes: The chart reflects how exposed different “education groups” of workers are on average to the three technology measures. Education groups are defined as the subsample of occupation-sector cells whose average educational attainment is in the lower, middle, and upper third (tercile) respectively of the national education distribution.

What do the results say about the impact of AI on employment?

We find a positive association between AI-enabled automation and changes in employment shares in our sample of 16 European countries, regardless of which proxy we used. According to the AI exposure indicator proposed by Webb (2020), moving 25 centiles up along the distribution of exposure to AI is associated with a 2.6% increase in sector-occupation employment share, while using the measure provided by Felten et al. (2018, 2019) the estimated increase in the sector-occupation employment share is 4.3%. The estimated coefficients are displayed by the horizontal line in the left-hand and middle columns of Charts 2 and 3.

Technology-enabled automation might also affect the relative shares of employment at different skill levels and thus impact earnings inequality. The literature on job polarisation shows that medium-skilled workers in routine-intensive jobs tended to be replaced by computerisation (e.g. Autor et al, 2003; Goos et al, 2009). In contrast, it is often argued that AI-enabled automation is more likely to complement or replace jobs in occupations that employ high-skilled labour.

Panels (a) and (b) in Chart 2 show the estimated coefficients of the association between changes in employment and AI-enabled automation by level of education (broken down into terciles, i.e. the lower, middle and upper thirds of the population). Statistically significant coefficients are plotted in dark blue. For occupations where average educational attainment is in the low and medium-skill groups, AI exposure does not seem to shake things up significantly. However, for the high-skill group we find a positive and significant association: moving 25 centiles up along the distribution of exposure to AI appears to boost the sector-occupation employment share by 3.1% using Webb’s AI exposure indicator, and by 6.7% using the measure of Felten et al.

Exposure to technology and changes in employment shares by skill level

a) AI, Webb b) AI, Felten et al. c) Software, Webb

percentage changes

Notes: Regression coefficients measuring the effect of exposure to technology on changes in employment share. Each observation is a ISCO 3-digit occupation times sector cell. Observations are weighted by cells’ average labour supply. Sector and country dummies are included. The sample consists in data for 16 European countries, from 2011 to 2019. The coefficient for the whole sample is shown by the horizontal line. The bars display the coefficient estimated for the subsample of cells for average educational attainment in the lower, middle and upper tercile respectively of the within-country education distribution. Coefficients that are statistically significant at least at the 10% level are plotted in dark blue.

Panels (a) and (b) in Chart 3 report the estimates by age group (again broken down by terciles, i.e. youngest, middle and oldest third of the population). AI-enabled automation appears to be more favourable for those occupations that employ relatively younger workers. Regardless of the AI indicator used, the estimated benefit for the younger group seems to be double that for the other age groups.

AI-enabled automation is thus associated with employment increases in Europe – mostly for high-skill occupations and younger workers. This is at odds with the evidence from previous technology waves, when computerisation decreased the relative share of employment of medium-skilled workers, resulting in polarisation. However, we do not find evidence of this polarisation pattern for our sample, e ven when examining the impact of software-enabled automation, proxied by the software exposure by Webb (2020). Panel (c) in Charts 2 and 3 displays the results. The relationship between software exposure and employment changes is null for the pooled sample, and there is no evidence of software replacing routine medium-skill jobs.

Exposure to technology and changes in employment shares by age

a) AI, Webb b) AI, Felten et al. C) Software, Webb

Notes: Regression coefficients measuring the effect of exposure to technology on changes in employment share. Each observation is an ISCO 3-digit occupation times sector cell. Observations are weighted by cells’ average labour supply. Sector and country dummies are included. The sample consists in data for 16 European countries, from 2011 to 2019. The coefficient for the whole sample is shown by the horizontal line. The bars display the coefficient estimated for the subsample of cells of workers with an average age in the lower, middle and upper tercile respectively of workers’ age distribution. Coefficients that are statistically significant at least at the 10% level are plotted in dark blue.

Despite the results for employment shares, neither AI or software exposure showed statistically significant effects on wages, except when using the Felten et al. measure, which indicates that occupations more exposed to AI have slightly worse wage growth.

Our results show a mixed picture across the 16 European countries. The positive impact of AI-enabled automation on employment holds true for most countries, with only a few exceptions. However, the scale of the impact varies substantially across countries. This might reflect differences in underlying economic factors, such as the pace of technology diffusion and education, or the level of regulation – and therefore competition – in product and labour markets.

Too soon to reach a verdict

During the deep learning boom of the 2010s, occupations potentially more exposed to AI-enabled technologies actually increased their employment share in Europe. Occupations with a relatively higher proportion of younger and skilled workers gained the most. For wages, the evidence is less clear and suggests neutral to slightly negative impacts. These results do not amount to an acquittal: AI-enabled technologies continue to be developed and adopted. Most of their impact on employment and wages – and therefore on growth and equality – has yet to be seen.

Acemoglu, D (2022), “Harms of AI”, Oxford Handbook of AI Governance .

Acemoglu, D., Autor, D., Hazell, J. and Restrepo, P. (2022), “Artificial intelligence and jobs: Evidence from online vacancies”, Journal of Labor Economics, Vol. 40(S1), pp. S293-S340.

Acemoglu, D. and Restrepo, P. (2018), “The race between man and machine: implications of technology for growth, factor shares, and employment”, American Economic Review , Vol. 108, pp. 1488-1542.

Albanesi, S., Dias da Silva, A., Jimeno, J. F., Lamo, A. and Wabitsch, A. (2023), “ New Technologies and Jobs in Europe ”, Working Paper Series, No 2831, ECB.

Autor, D. (2015), “Why are there still so many jobs? The history and future of workplace automation”, Journal of Economic Perspectives , Vol.29(3), pp. 3-30.

Autor, D., Levy, F. and Murnane, R. (2003), “The skill content of recent technological change: An empirical exploration”, Quarterly Journal of Economics, Vol. 118(4), pp. 1279-1333.

Bessen, J. (2019), “Automation and jobs: when technology boosts employment” , Economic Policy , October, pp. 589-626.

Felten, E. W., Raj, M. and Seamans, R. (2018), “A method to link advances in artificial intelligence to occupational abilities”, AEA Papers and Proceedings, Vol. 108, pp. 54–57.

Felten, E. W., Raj, M. and Seamans, R. (2019), “The effect of artificial intelligence on human labor: An ability-based approach”, Academy of Management Proceedings .

Frey, C. B. and Osborne M. A. (2017), “The future of employment: How susceptible are jobs to computerisation?”, Technological Forecasting and Social Change , Vol. 114, pp. 254-280.

Goos, M., Manning, A. and Salomons, A. (2009), “Job polarization in Europe”, American Economic Review , Vol. 99(2), pp. 58-63.

Susskind, D. (2020), A world without work: Technology, automation and how we should respond , London: Penguin.

Webb, M. (2020), The impact of artificial intelligence on the labor market, mimeo.

This article was written by Stefania Albanesi (University of Pittsburg, NBER and CEPS), António Dias da Silva (Directorate General Economics, European Central Bank), Juan Francisco Jimeno (Banco de España, Universidad de Alcalá, CEMFI, CEPR and IZA), Ana Lamo (Directorate General Research, European Central Bank) and Alena Wabitsch (University of Oxford). It is based on the paper entitled “New technologies and jobs in Europe” by the same authors. The authors would like to thank Gareth Budden, Michael Ehrmann, Alex Popov and Zoë Sprokel for their comments. The views expressed here are those of the authors and do not necessarily represent the views of the European Central Bank and the Eurosystem.

Belgium, Germany, Estonia, Ireland, Greece, Spain, France, Italy, Latvia, Lithuania, Luxembourg, Netherlands, Austria, Portugal, Finland and the United Kingdom.

The Occupational Information Network (O*NET) is an online database that contains hundreds of job definitions in the United States. Every occupation requires a different mix of knowledge, skills and abilities, and is performed using a variety of activities and tasks.

Our website uses cookies

We are always working to improve this website for our users. To do this, we use the anonymous data provided by cookies. Learn more about how we use cookies

We have updated our privacy policy

We are always working to improve this website for our users. To do this, we use the anonymous data provided by cookies. See what has changed in our privacy policy

Your cookie preference has expired