literature review on generators

Revolutionize Your Research with Jenni AI

Literature Review Generator

Welcome to Jenni AI, the ultimate tool for researchers and students. Our AI Literature Review Generator is designed to assist you in creating comprehensive, high-quality literature reviews, enhancing your academic and research endeavors. Say goodbye to writer's block and hello to seamless, efficient literature review creation.

Loved by over 1 million academics

Endorsed by Academics from Leading Institutions

Join the Community of Scholars Who Trust Jenni AI

Elevate Your Research Toolkit

Discover the Game-Changing Features of Jenni AI for Literature Reviews

Advanced AI Algorithms

Jenni AI utilizes cutting-edge AI technology to analyze and suggest relevant literature, helping you stay on top of current research trends.

Get started

Idea Generation

Overcome writer's block with AI-generated prompts and ideas that align with your research topic, helping to expand and deepen your review.

Citation Assistance

Get help with proper citation formats to maintain academic integrity and attribute sources correctly.

Our Pledge to Academic Integrity

At Jenni AI, we are deeply committed to the principles of academic integrity. We understand the importance of honesty, transparency, and ethical conduct in the academic community. Our tool is designed not just to assist in your research, but to do so in a way that respects and upholds these fundamental values.

How it Works

Start by creating your account on Jenni AI. The sign-up process is quick and user-friendly.

Define Your Research Scope

Enter the topic of your literature review to guide Jenni AI’s focus.

Citation Guidance

Receive assistance in citing sources correctly, maintaining the academic standard.

Easy Export

Export your literature review to LaTeX, HTML, or .docx formats

Interact with AI-Powered Suggestions

Use Jenni AI’s suggestions to structure your literature review, organizing it into coherent sections.

What Our Users Say

Discover how Jenni AI has made a difference in the lives of academics just like you

· Aug 26

I thought AI writing was useless. Then I found Jenni AI, the AI-powered assistant for academic writing. It turned out to be much more advanced than I ever could have imagined. Jenni AI = ChatGPT x 10.

Charlie Cuddy

@sonofgorkhali

· 23 Aug

Love this use of AI to assist with, not replace, writing! Keep crushing it @Davidjpark96 💪

Waqar Younas, PhD

@waqaryofficial

· 6 Apr

4/9 Jenni AI's Outline Builder is a game-changer for organizing your thoughts and structuring your content. Create detailed outlines effortlessly, ensuring your writing is clear and coherent. #OutlineBuilder #WritingTools #JenniAI

I started with Jenni-who & Jenni-what. But now I can't write without Jenni. I love Jenni AI and am amazed to see how far Jenni has come. Kudos to http://Jenni.AI team.

· 28 Jul

Jenni is perfect for writing research docs, SOPs, study projects presentations 👌🏽

Stéphane Prud'homme

http://jenni.ai is awesome and super useful! thanks to @Davidjpark96 and @whoisjenniai fyi @Phd_jeu @DoctoralStories @WriteThatPhD

Frequently asked questions

What exactly does jenni ai do, is jenni ai suitable for all academic disciplines, is there a trial period or a free version available.

How does Jenni AI help with writer's block?

Can Jenni AI write my literature review for me?

How often is the literature database updated in Jenni AI?

How user-friendly is Jenni AI for those not familiar with AI tools?

Jenni AI: Standing Out From the Competition

In a sea of online proofreaders, Jenni AI stands out. Here’s how we compare to other tools on the market:

Feature Featire

COMPETITORS

Advanced AI-Powered Assistance

Uses state-of-the-art AI technology to provide relevant literature suggestions and structural guidance.

May rely on simpler algorithms, resulting in less dynamic or comprehensive support.

User-Friendly Interface

Designed for ease of use, making it accessible for users with varying levels of tech proficiency.

Interfaces can be complex or less intuitive, posing a challenge for some users.

Transparent and Flexible Pricing

Offers a free trial and clear, flexible pricing plans suitable for different needs.

Pricing structures can be opaque or inflexible, with fewer user options.

Unparalleled Customization

Offers highly personalized suggestions and adapts to your specific research needs over time.

Often provide generic suggestions that may not align closely with individual research topics.

Comprehensive Literature Access

Provides access to a vast and up-to-date range of academic literature, ensuring comprehensive research coverage.

Some may have limited access to current or diverse research materials, restricting the scope of literature reviews.

Literature Review Generator by AcademicHelp

Features of Our Literature Review Generator

Advanced power of AI

Simplified information gathering

Enhanced quality

Free literature review generator.

Remember Me

What is your profession ? Student Teacher Writer Other

Forgotten Password?

Username or Email

Something went wrong when searching for seed articles. Please try again soon.

No articles were found for that search term.

Author, year The title of the article goes here

LITERATURE REVIEW SOFTWARE FOR BETTER RESEARCH

“This tool really helped me to create good bibtex references for my research papers”

Ali Mohammed-Djafari

Director of Research at LSS-CNRS, France

“Any researcher could use it! The paper recommendations are great for anyone and everyone”

Swansea University, Wales

“As a student just venturing into the world of lit reviews, this is a tool that is outstanding and helping me find deeper results for my work.”

Franklin Jeffers

South Oregon University, USA

“One of the 3 most promising tools that (1) do not solely rely on keywords, (2) does nice visualizations, (3) is easy to use”

Singapore Management University

“Incredibly useful tool to get to know more literature, and to gain insight in existing research”

KU Leuven, Belgium

“Seeing my literature list as a network enhances my thinking process!”

Katholieke Universiteit Leuven, Belgium

“I can’t live without you anymore! I also recommend you to my students.”

Professor at The Chinese University of Hong Kong

“This has helped me so much in researching the literature. Currently, I am beginning to investigate new fields and this has helped me hugely”

Aran Warren

Canterbury University, NZ

“It's nice to get a quick overview of related literature. Really easy to use, and it helps getting on top of the often complicated structures of referencing”

Christoph Ludwig

Technische Universität Dresden, Germany

“Litmaps is extremely helpful with my research. It helps me organize each one of my projects and see how they relate to each other, as well as to keep up to date on publications done in my field”

Daniel Fuller

Clarkson University, USA

“Litmaps is a game changer for finding novel literature... it has been invaluable for my productivity.... I also got my PhD student to use it and they also found it invaluable, finding several gaps they missed”

Varun Venkatesh

Austin Health, Australia

Our Course: Learn and Teach with Litmaps

RAxter is now Enago Read! Enjoy the same licensing and pricing with enhanced capabilities. No action required for existing customers.

Your all in one AI-powered Reading Assistant

A Reading Space to Ideate, Create Knowledge, and Collaborate on Your Research

• Smartly organize your research
• Receive recommendations that cannot be ignored
• Collaborate with your team to read, discuss, and share knowledge

From Surface-Level Exploration to Critical Reading - All in one Place!

Fine-tune your literature search.

Our AI-powered reading assistant saves time spent on the exploration of relevant resources and allows you to focus more on reading.

Select phrases or specific sections and explore more research papers related to the core aspects of your selections. Pin the useful ones for future references.

Our platform brings you the latest research related to your and project work.

Speed up your literature review

Quickly generate a summary of key sections of any paper with our summarizer.

Make informed decisions about which papers are relevant, and where to invest your time in further reading.

Get key insights from the paper, quickly comprehend the paper’s unique approach, and recall the key points.

Bring order to your research projects

Organize your reading lists into different projects and maintain the context of your research.

Quickly sort items into collections and tag or filter them according to keywords and color codes.

Experience the power of sharing by finding all the shared literature at one place.

Decode papers effortlessly for faster comprehension

Highlight what is important so that you can retrieve it faster next time.

Select any text in the paper and ask Copilot to explain it to help you get a deeper understanding.

Ask questions and follow-ups from AI-powered Copilot.

Collaborate to read with your team, professors, or students

Share and discuss literature and drafts with your study group, colleagues, experts, and advisors. Recommend valuable resources and help each other for better understanding.

Work in shared projects efficiently and improve visibility within your study group or lab members.

Keep track of your team's progress by being constantly connected and engaging in active knowledge transfer by requesting full access to relevant papers and drafts.

Find papers from across the world's largest repositories

Testimonials

Privacy and security of your research data are integral to our mission..

Everything you add or create on Enago Read is private by default. It is visible if and when you share it with other users.

You can put Creative Commons license on original drafts to protect your IP. For shared files, Enago Read always maintains a copy in case of deletion by collaborators or revoked access.

We use state-of-the-art security protocols and algorithms including MD5 Encryption, SSL, and HTTPS to secure your data.

• Resources Home 🏠
• Try SciSpace Copilot
• Search research papers
• Add Copilot Extension
• Try AI Detector
• Try Paraphraser
• Try Citation Generator
• April Papers
• June Papers
• July Papers

5 literature review tools to ace your research (+2 bonus tools)

Table of Contents

Your literature review is the lore behind your research paper . It comes in two forms, systematic and scoping , both serving the purpose of rounding up previously published works in your research area that led you to write and finish your own.

A literature review is vital as it provides the reader with a critical overview of the existing body of knowledge, your methodology, and an opportunity for research applications.

Some steps to follow while writing your review:

• Pick an accessible topic for your paper
• Do thorough research and gather evidence surrounding your topic
• Read and take notes diligently
• Create a rough structure for your review
• Synthesis your notes and write the first draft
• Edit and proofread your literature review

To make your workload a little lighter, there are many literature review AI tools. These tools can help you find academic articles through AI and answer questions about a research paper.  

Best literature review tools to improve research workflow

A literature review is one of the most critical yet tedious stages in composing a research paper. Many students find it an uphill task since it requires extensive reading and careful organization .

Using some of the best literature review tools listed here, you can make your life easier by overcoming some of the existing challenges in literature reviews. From collecting and classifying to analyzing and publishing research outputs, these tools help you with your literature review and improve your productivity without additional effort or expenses.

1. SciSpace

SciSpace is an AI for academic research that will help find research papers and answer questions about a research paper. You can discover, read, and understand research papers with SciSpace making it an excellent platform for literature review. Featuring a repository with over 270 million research papers, it comes with your AI research assistant called Copilot that offers explanations, summaries , and answers as you read.

Get started now:

Find academic articles through AI

SciSpace has a dedicated literature review tool that finds scientific articles when you search for a question. Based on semantic search, it shows all the research papers relevant for your subject. You can then gather quick insights for all the papers displayed in your search results like methodology, dataset, etc., and figure out all the papers relevant for your research.

Identify relevant articles faster

Abstracts are not always enough to determine whether a paper is relevant to your research question. For starters, you can ask questions to your AI research assistant, SciSpace Copilot to explore the content and better understand the article. Additionally, use the summarize feature to quickly review the methodology and results of a paper and decide if it is worth reading in detail.

Learn in your preferred language

A big barrier non-native English speakers face while conducting a literature review is that a significant portion of scientific literature is published in English. But with SciSpace Copilot, you can review, interact, and learn from research papers in any language you prefer — presently, it supports 75+ languages. The AI will answer questions about a research paper in your mother tongue.

Integrates with Zotero

Many researchers use Zotero to create a library and manage research papers. SciSpace lets you import your scientific articles directly from Zotero into your SciSpace library and use Copilot to comprehend your research papers. You can also highlight key sections, add notes to the PDF as you read, and even turn helpful explanations and answers from Copilot into notes for future review.

Understand math and complex concepts quickly

Come across complex mathematical equations or difficult concepts? Simply highlight the text or select the formula or table, and Copilot will provide an explanation or breakdown of the same in an easy-to-understand manner. You can ask follow-up questions if you need further clarification.

Discover new papers to read without leaving

Highlight phrases or sentences in your research paper to get suggestions for related papers in the field and save time on literature reviews. You can also use the 'Trace' feature to move across and discover connected papers, authors, topics, and more.

SciSpace Copilot is now available as a Chrome extension , allowing you to access its features directly while you browse scientific literature anywhere across the web.

Get citation-backed answers

When you're conducting a literature review, you want credible information with proper references.  Copilot ensures that every piece of information provided by SciSpace Copilot is backed by a direct reference, boosting transparency, accuracy, and trustworthiness.

Ask a question related to the paper you're delving into. Every response from Copilot comes with a clickable citation. This citation leads you straight to the section of the PDF from which the answer was extracted.

By seamlessly integrating answers with citations, SciSpace Copilot assures you of the authenticity and relevance of the information you receive.

2. Mendeley

Mendeley Citation Manager is a free web and desktop application. It helps simplify your citation management workflow significantly. Here are some ways you can speed up your referencing game with Mendeley.

Generate citations and bibliographies

Easily add references from your Mendeley library to your Word document, change your citation style, and create a bibliography, all without leaving your document.

Retrieve references

It allows you to access your references quickly. Search for a term, and it will return results by referencing the year, author, or source.

Add sources to your Mendeley library by dragging PDF to Mendeley Reference Manager. Mendeley will automatically remove the PDF(s) metadata and create a library entry.‌

Read and annotate documents

It helps you highlight and comment across multiple PDFs while keep them all in one place using Mendeley Notebook . Notebook pages are not tied to a reference and let you quote from many PDFs.

A big part of many literature review workflows, Zotero is a free, open-source tool for managing citations that works as a plug-in on your browser. It helps you gather the information you need, cite your sources, lets you attach PDFs, notes, and images to your citations, and create bibliographies.

Import research articles to your database

Search for research articles on a keyword, and add relevant results to your database. Then, select the articles you are most interested in, and import them into Zotero.

Add bibliography in a variety of formats

With Zotero, you don’t have to scramble for different bibliography formats. Simply use the Zotero-Word plug-in to insert in-text citations and generate a bibliography.

Share your research

You can save a paper and sync it with an online library to easily share your research for group projects. Zotero can be used to create your database and decrease the time you spend formatting citations.

Sysrev is an AI too for article review that facilitates screening, collaboration, and data extraction from academic publications, abstracts, and PDF documents using machine learning. The platform is free and supports public and Open Access projects only.

Some of the features of Sysrev include:

Group labels

Group labels can be a powerful concept for creating database tables from documents. When exported and re-imported, each group label creates a new table. To make labels for a project, go into the manage -> labels section of the project.

Group labels enable project managers to pull table information from documents. It makes it easier to communicate review results for specific articles.

Track reviewer performance

Sysrev's label counting tool provides filtering and visualization options for keeping track of the distribution of labels throughout the project's progress. Project managers can check their projects at any point to track progress and the reviewer's performance.

Tool for concordance

The Sysrev tool for concordance allows project administrators and reviewers to perform analysis on their labels. Concordance is measured by calculating the number of times users agree on the labels they have extracted.

Colandr is a free, open-source, internet-based analysis and screening software used as an AI for academic research. It was designed to ease collaboration across various stages of the systematic review procedure. The tool can be a little complex to use. So, here are the steps involved in working with Colandr.

Create a review

The first step to using Colandr is setting up an organized review project. This is helpful to librarians who are assisting researchers with systematic reviews.

The planning stage is setting the review's objectives along with research queries. Any reviewer can review the details of the planning stage. However, they can only be modified by the author for the review.

Citation screening/import

In this phase, users can upload their results from database searches. Colandr also offers an automated deduplication system.

Full-text screening

The system in Colandr will discover the combination of terms and expressions that are most useful for the reader. If an article is selected, it will be moved to the final step.

Data extraction/export

Colandr data extraction is more efficient than the manual method. It creates the form fields for data extraction during the planning stage of the review procedure. Users can decide to revisit or modify the form for data extraction after completing the initial screening.

Bonus literature review tools

SRDR+ is a web-based tool for extracting and managing systematic review or meta-analysis data. It is open and has a searchable archive of systematic reviews and their data.

7. Plot Digitizer

Plot Digitizer is an efficient tool for extracting information from graphs and images, equipped with many features that facilitate data extraction. The program comes with a free online application, which is adequate to extract data quickly.

Final thoughts

Writing a literature review is not easy. It’s a time-consuming process, which can become tiring at times. The literature review tools mentioned in this blog do an excellent job of maximizing your efforts and helping you write literature reviews much more efficiently. With them, you can breathe a sigh of relief and give more time to your research.

As you dive into your literature review, don’t forget to use SciSpace ResearchGPT to streamline the process. It facilitates your research and helps you explore key findings, summary, and other components of the paper easily.

Frequently Asked Questions (FAQs)

1. what is rrl in research.

RRL stands for Review of Related Literature and sometimes interchanged with ‘Literature Review.’ RRL is a body of studies relevant to the topic being researched. These studies may be in the form of journal articles, books, reports, and other similar documents. Review of related literature is used to support an argument or theory being made by the researcher, as well as to provide information on how others have approached the same topic.

2. What are few softwares and tools available for literature review?

• SciSpace Discover

• Mendeley

• Zotero

• Sysrev

• Colandr

• SRDR+

3. How to generate an online literature review?

The Scispace Discover tool, which offers an excellent repository of millions of peer-reviewed articles and resources, will help you generate or create a literature review easily. You may find relevant information by utilizing the filter option, checking its credibility, tracing related topics and articles, and citing in widely accepted formats with a single click.

4. What does it mean to synthesize literature?

To synthesize literature is to take the main points and ideas from a number of sources and present them in a new way. The goal is to create a new piece of writing that pulls together the most important elements of all the sources you read. Make recommendations based on them, and connect them to the research.

5. Should we write abstract for literature review?

Abstracts, particularly for the literature review section, are not required. However, an abstract for the research paper, on the whole, is useful for summarizing the paper and letting readers know what to expect from it. It can also be used to summarize the main points of the paper so that readers have a better understanding of the paper's content before they read it.

6. How do you evaluate the quality of a literature review?

• Whether it is clear and well-written.

• Whether Information is current and up to date.

• Does it cover all of the relevant sources on the topic.

• Does it provide enough evidence to support its conclusions.

7. Is literature review mandatory?

Yes. Literature review is a mandatory part of any research project. It is a critical step in the process that allows you to establish the scope of your research and provide a background for the rest of your work.

8. What are the sources for a literature review?

• Reports

• Theses

• Conference proceedings

• Company reports

• Some government publications

• Journals

• Books

• Newspapers

• Articles by professional associations

• Indexes

• Databases

• Catalogues

• Encyclopaedias

• Dictionaries

• Bibliographies

• Citation indexes

• Statistical data from government websites

9. What is the difference between a systematic review and a literature review?

A systematic review is a form of research that uses a rigorous method to generate knowledge from both published and unpublished data. A literature review, on the other hand, is a critical summary of an area of research within the context of what has already been published.

Suggested reads!

Types of essays in academic writing Citation Machine Alternatives — A comparison of top citation tools 2023

QuillBot vs SciSpace: Choose the best AI-paraphrasing tool

ChatPDF vs. SciSpace Copilot: Unveiling the best tool for your research

You might also like

Consensus GPT vs. SciSpace GPT: Choose the Best GPT for Research

Literature Review and Theoretical Framework: Understanding the Differences

Types of Essays in Academic Writing - Quick Guide (2024)

AI Literature Review Generator

Effortlessly generate comprehensive literature reviews with our AI-powered tool, saving time and enhancing research quality.

2M+ Professionals choose us

AI Review Benefits

Time-saving.

Generate detailed literature reviews in less time, allowing you to focus on research and analysis.

Enhanced Quality

Produce comprehensive and high-quality literature reviews with the assistance of advanced AI algorithms.

Improved Efficiency

Streamline your research process by efficiently generating literature reviews using AI technology.

AI Literature Review Generator Benefits

Efficient research.

AI writing tools offer a comprehensive database for literature review, accelerating the research process. By providing access to a vast collection of scholarly articles, these tools save time and effort that would otherwise be spent on manual searches. Researchers can swiftly identify relevant sources, enhancing the efficiency of their literature review process.

Moreover, the ability to filter search results based on specific criteria ensures that the retrieved content aligns with the research requirements. This precision in sourcing information streamlines the review process, enabling researchers to focus on analyzing and synthesizing the gathered data.

Enhanced Content Quality

Utilizing AI tools for writing elevates the quality of literature reviews by offering advanced language processing capabilities. These tools facilitate the identification of key themes, trends, and insights within the literature, enabling researchers to produce more in-depth and well-structured reviews.

Additionally, the automated citation and referencing features ensure accuracy and consistency in academic writing, saving researchers from the tedious task of manually managing citations. This not only enhances the overall quality of the literature review but also reduces the likelihood of errors.

Collaborative Capabilities

Online writing tools foster seamless collaboration among researchers by providing features for shared document editing and real-time feedback. This collaborative environment promotes effective teamwork, allowing multiple contributors to collectively work on the literature review, share insights, and provide constructive feedback.

Furthermore, these tools offer version history tracking, ensuring transparency and accountability in the collaborative writing process. With the ability to track changes and contributions, researchers can easily monitor the evolution of the literature review and attribute specific contributions to team members.

Best AI Writing Tools - Useful Tips

Utilize advanced features.

When using the best AI tools for writing, explore advanced features such as natural language processing and sentiment analysis to gain deeper insights from the literature. These features can help in identifying underlying emotions, biases, and perspectives within the reviewed content, adding depth to the analysis.

Moreover, leverage the data visualization capabilities offered by AI writing tools to present the literature review findings in an engaging and comprehensible manner, enhancing the overall impact of the research.

Continuous Learning

Stay updated with the latest advancements in AI writing tools for authors to harness the full potential of these technologies. Regularly explore new features, updates, and best practices to optimize the efficiency and effectiveness of literature review generation.

Engaging in continuous learning ensures that researchers remain at the forefront of utilizing AI tools for writing, empowering them to leverage cutting-edge capabilities for producing high-quality literature reviews.

Optimize Collaboration

Maximize the collaborative benefits of AI writing tools by establishing clear communication channels and defining roles within the research team. Effective communication ensures that all team members are aligned with the literature review goals and enables streamlined coordination in the review process.

Additionally, establish regular checkpoints to review the progress and address any challenges, fostering a collaborative environment that maximizes the collective expertise of the research team.

Customize Search Parameters

Tailor the search parameters within AI literature review generators to align with the specific research objectives. By customizing search filters based on publication dates, relevance, or specific keywords, researchers can refine the search results to precisely match the requirements of the literature review.

This customization enhances the accuracy and relevance of the retrieved literature, ensuring that the generated review is comprehensive and aligned with the research focus.

Utilize Citation Management

Effectively utilize the citation management features offered by AI writing tools for authors to streamline the referencing process. Organize and manage citations seamlessly, ensuring adherence to the required citation styles and formatting guidelines throughout the literature review.

By leveraging these citation management capabilities, researchers can maintain consistency and accuracy in citing sources, enhancing the credibility and scholarly integrity of the literature review.

How to use Article Generator

Choose a template.

Select the necessary template from the template gallery.

Provide more details

Fill out the carefully selected inputs to create the best quality of output content.

Enjoy the results

Copy, save for later, rate the output or hit regenerate button.

AI Literature Review Generator Examples

Discover the power of AI literature review generators with these practical examples showcasing their effectiveness in generating comprehensive and insightful literature reviews tailored to specific research queries.

Craft a comprehensive literature review addressing the impact of AI in medical research, highlighting the advancements, challenges, and future implications of AI integration in healthcare.

AI literature review generators provide a valuable resource for synthesizing the extensive body of medical research related to artificial intelligence. By inputting specific keywords such as 'AI in healthcare' and 'medical research advancements,' the tool swiftly retrieves a diverse range of scholarly articles, enabling the identification of key themes and insights.

The generated literature review encompasses a comprehensive analysis of the impact of AI in medical research, encapsulating the advancements, challenges, and future implications of AI integration in healthcare. Through the tool's advanced natural language processing capabilities, the review delves into the underlying perspectives, sentiments, and potential biases within the analyzed literature, providing a nuanced understanding of the subject matter.

Furthermore, the AI writing tool streamlines the citation and referencing process, ensuring the accurate attribution of sources and adherence to citation guidelines. The collaborative features of the tool facilitate seamless teamwork, allowing multiple researchers to collectively contribute to the literature review, share insights, and refine the analysis.

The generated literature review is presented with compelling data visualizations, effectively conveying the synthesized information in a visually engaging format. This example underscores the efficacy of AI literature review generators in producing comprehensive and insightful reviews tailored to specific research queries, showcasing their indispensable role in advancing medical research and scholarly discourse.

Create a literature review exploring the intersection of AI and environmental studies, focusing on the applications, implications, and ethical considerations of AI technologies in environmental research and conservation.

For researchers delving into the intersection of AI and environmental studies, AI literature review generators offer a robust platform for consolidating a diverse array of scholarly resources. By inputting targeted keywords such as 'AI applications in environmental research' and 'ethical considerations of AI in conservation,' the tool retrieves an extensive range of literature, enabling the synthesis of key insights and perspectives.

The generated literature review provides a comprehensive exploration of the applications, implications, and ethical considerations of AI technologies in environmental studies and conservation. Leveraging the tool's advanced features, the review delves into the nuanced perspectives and sentiments within the analyzed content, enhancing the depth of the analysis.

Moreover, the citation management capabilities of the AI writing tool ensure the seamless organization and adherence to citation guidelines, maintaining the scholarly integrity of the review. The collaborative environment facilitated by the tool allows researchers to collectively contribute to the literature review, fostering an environment of shared insights and collaborative refinement.

The literature review is presented with impactful data visualizations, effectively conveying the synthesized information in an engaging manner. This example exemplifies the effectiveness of AI literature review generators in generating comprehensive and insightful reviews tailored to specific research queries, illustrating their pivotal role in advancing environmental research and fostering informed discourse.

Frequently Asked Questions

What is an ai literature review generator, how do ai writing tools benefit literature review creation, what are some examples of ai-powered writing assistance tools, why use ai-powered writing tools for literature review generation, how can ai writing tools improve the quality of literature reviews, where can i find the best ai writing tools for literature review creation, join 1,000,000+ creators and professionals from trusted companies by choosing us, .css-1d7fhal{margin:0;font-family:"roboto","helvetica","arial",sans-serif;font-weight:400;font-size:1rem;line-height:1.5;letter-spacing:0.00938em;max-width:700px;}@media (min-width:0px){.css-1d7fhal{font-size:24px;font-weight:600;line-height:32px;font-family:'__inter_6eddd9','__inter_fallback_6eddd9';}}@media (min-width:744px){.css-1d7fhal{font-size:45px;font-weight:600;line-height:52px;font-family:'__inter_6eddd9','__inter_fallback_6eddd9';}} have a task that has no tool our chat knows how to do it.

HTML conversions sometimes display errors due to content that did not convert correctly from the source. This paper uses the following packages that are not yet supported by the HTML conversion tool. Feedback on these issues are not necessary; they are known and are being worked on.

• failed: arydshln
• failed: inconsolata

Authors: achieve the best HTML results from your LaTeX submissions by following these best practices .

LitLLM: A Toolkit for Scientific Literature Review

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate—generate non-factual information—and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our open-source toolkit is accessible at https://github.com/shubhamagarwal92/LitLLM and Huggingface space ( https://huggingface.co/spaces/shubhamagarwal92/LitLLM ) with the video demo at https://youtu.be/E2ggOZBAFw0

Shubham Agarwal 1,2,3 , Issam H. Laradji 1,4 , Laurent Charlin 2,3,5 , Christopher Pal 1,2,5 1 ServiceNow Research, 2 Mila - Quebec AI Institute, 3 HEC Montreal, Canada 4 UBC, Vancouver, Canada, 5 Canada CIFAR AI Chair Correspondence: [email protected]

1 Introduction

Scientists have long used NLP systems like search engines to find and retrieve relevant papers. Scholarly engines, including Google Scholar, Microsoft Academic Graph, and Semantic Scholar, provide additional tools and structure to help researchers further. Following recent advances in large language models (LLMs), a new set of systems provides even more advanced features. For example, Explainpaper 1 1 1 https://www.explainpaper.com/ helps explain the contents of papers, and Writefull 2 2 2 https://x.writefull.com/ helps with several writing tasks, including abstract and title generation. There are, of course, many other tasks where similar technologies could be helpful.

Systems that help researchers with literature reviews hold promising prospects. The literature review is a difficult task that can be decomposed into several sub-tasks, including retrieving relevant papers and generating a related works section that contextualizes the proposed work compared to the existing literature. It is also a task where factual correctness is essential. In that sense, it is a challenging task for current LLMs, which are known to hallucinate. Overall, creating tools to help researchers more rapidly identify, summarize and contextualize relevant prior work could significantly help the research community.

Recent works explore the task of literature review in parts or in full. For example, Lu et al. ( 2020 ) proposes generating the related works section of a paper using its abstract and a list of (relevant) references. Researchers also look at the whole task and build systems using LLMs like ChatGPT for literature review  Haman and Školník ( 2023 ); Huang and Tan ( 2023 ) . While these LLMs tend to generate high-quality text, they are prone to hallucinations  Athaluri et al. ( 2023 ) . For example, the Galactica system was developed to reason about scientific knowledge (Taylor et al., 2022 ) . While it outperforms contemporary models on various scientific tasks, it generates made-up content like inaccurate citations and imaginary papers. 3 3 3 see e.g., What Meta Learned from Galactica

As a step forward, we explore retrieval-augmented-generation (RAG) to improve factual correctness  Lewis et al. ( 2020 ) . The idea is to use the retrieval mechanism to obtain a relevant list of existing papers to be cited which provides relevant contextual knowledge for LLM based generation.

LitLLM is an interactive tool to help scientists write the literature review or related work section of a scientific paper starting from a user-provided abstract (see Figure  1 ). The specific objectives of this work are to create a system to help users navigate through research papers and write a literature review for a given paper or project. Our main contributions are:

We provide a system based on a modular pipeline that conducts a literature review based on a user-proposed abstract.

We use Retrieval Augmented Generation (RAG) techniques to condition the generated related work on factual content and avoid hallucinations using multiple search techniques.

We incorporate sentence-based planning to promote controllable generation.

2 Related Work

LLMs have demonstrated significant capabilities in storing factual knowledge and achieving state-of-the-art results when fine-tuned on downstream Natural Language Processing (NLP) tasks   Lewis et al. ( 2020 ) .

However, they also face challenges such as hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes   Huang et al. ( 2023 ); Gao et al. ( 2023 ); Li et al. ( 2024 ) . These limitations have motivated the development of RAG (Retrieval Augmented Generation), which incorporates knowledge from external databases to enhance the accuracy and credibility of the models, particularly for knowledge-intensive tasks   Gao et al. ( 2023 ) . RAG has emerged as a promising solution to the challenges faced by LLMs. It synergistically merges LLMs’ intrinsic knowledge with the vast, dynamic repositories of external databases   Gao et al. ( 2023 ) . This approach allows for continuous knowledge updates and integration of domain-specific information in an attempt to limit the effect of outdated knowledge. The proposed work builds upon the advancements around RAG to provide a more efficient solution for academic writing.

On the other hand, there has been a notable emphasis on utilizing Large Language Models (LLMs) for tasks related to information retrieval and ranking   Zhu et al. ( 2023 ) . The work by  Sun et al. ( 2023 ) leverages generative LLMs such as ChatGPT and GPT-4 for relevance ranking in information retrieval, demonstrating that these models can deliver competitive results to state-of-the-art supervised methods. Pradeep et al. ( 2023b , a ) introduce different open-source LLM for listwise zero-shot reranking, further motivating the proposed approach of using LLMs for reranking in our work.

The exploration of large language models (LLMs) and their zero-shot abilities has been a significant focus in recent research. For instance, one study investigated using LLMs in recommender systems, demonstrating their promising zero-shot ranking abilities, although they struggled with the order of historical interactions and position bias   Hou et al. ( 2023 ) . Another study improved the zero-shot learning abilities of LLMs through instruction tuning, which led to substantial improvements in performance on unseen tasks   Wei et al. ( 2021 ) . A similar approach was taken to enhance the zero-shot reasoning abilities of LLMs, with the introduction of an autonomous agent to instruct the reasoning process, resulting in significant performance boosts   Crispino et al. ( 2023 ) . The application of LLMs has also been explored in the context of natural language generation (NLG) assessment, with comparative assessment found to be superior to prompt scoring   Liusie et al. ( 2023 ) . In the domain of Open-Domain Question Answering (ODQA), a Self-Prompting framework was proposed to utilize the massive knowledge stored in LLMs, leading to significant improvements over previous methods   Li et al. ( 2022 ) . Prompt engineering has been identified as a key technique for enhancing the abilities of LLMs, with various strategies being explored   Shi et al. ( 2023 ) . 4 4 4 This paragraph was generated using our platform with some minor modifications based on a slightly different version of our abstract.

Figure 2 provides an overview of the pipeline. The user provides a draft of the abstract or a research idea. We use LLM to first summarize the abstract in keywords that can be used as a query for search engines. Optionally, the users could provide relevant keywords to improve search results. This query is passed to the search engine, which retrieves relevant papers with the corresponding information, such as abstracts and open-access PDF URLs. These retrieved abstracts with the original query abstract are used as input to the other LLM Re-ranker, which provides a listwise ranking of the papers based on the relevance to the query abstract. These re-ranked abstracts with the original query are finally passed to the LLM generator, which generates the related work section of the paper. Recently, Agarwal et al. ( 2024 ) showed that prompting the LLMs with the sentence plans results in reduced hallucinations in the generation outputs. These plans contain information about the number of sentences and the citation description on each line, providing control to meet author preferences. We include this sentence-based planning in the LLM generator as part of this system. In the following, we provide more details about each of the modules.

3.1 Paper Retrieval Module

In our toolkit, we retrieve relevant papers using the Semantic Scholar API. Other platforms could be used, but the S2 Platform is well-adapted to this use case. It is a large-scale academic corpus comprising 200M+ metadata records across multiple research areas, providing information about papers’ metadata, authors, paper embedding, etc. The Recommendations API also provides relevant papers similar to any seed paper. Figure 3 shows our system’s different strategies. We describe these three settings that we use to search for references:

User provides an abstract or a research idea (roughly the length of the abstract). We prompt an LLM (see Figure 4 ) to summarize this abstract in keywords which can be used as a search query with most APIs.

Users can optionally also provide keywords that can improve search results. This is similar (in spirit) to how researchers search for related work with a search engine. This is particularly useful in interdisciplinary research, and authors would like to include the latest research from a particular domain, which could not be captured much in the abstract.

Lastly, any seed paper the user finds relevant enough to their idea could be used with the Recommendations API from search engines to provide other closely related papers.

3.2 Paper Re-Ranking Module

Recent efforts have explored the application of proprietary LLMs for ranking   Sun et al. ( 2023 ); Ma et al. ( 2023 ) as well as open-source models like   Pradeep et al. ( 2023a , b ) . These approaches provide a combined list of passages directly as input to the model and retrieve the re-ordered ranking list   Zhang et al. ( 2023 ) . Typically, a retriever first filters top-k potential candidates, which are then re-ranked by an LLM to provide the final output list. In our work, we use the instructional permutation generation approach  Sun et al. ( 2023 ) where the model is prompted to generate a permutation of the different papers in descending order based on the relevance to the user-provided abstract, thus producing an ordered list of preferences against providing intermediate scores. Figure 5 showcases the prompt we used for LLM-based re-ranking.

3.3 Summary Generation Module

We explore two strategies for generation: (1) Zero-shot generation and (2) Plan-based generation, which relies on sentence plans for controllable generation, described in the following

3.3.1 Zero-shot generation

While LLMs can potentially search and generate relevant papers from their parametric memory and trained data, they are prone to hallucinating and generating non-factual content. Retrieval augmented generation, first introduced in   Parvez et al. ( 2021 ) for knowledge tasks, addresses this by augmenting the generation model with an information retrieval module. The RAG principles have been subsequently used for dialogue generation in task-oriented settings  Thulke et al. ( 2021 ) , code generation  Liu et al. ( 2020 ); Parvez et al. ( 2021 ) and product review generation  Kim et al. ( 2020 ) . RAG drastically reduces hallucinations in the generated output  Gao et al. ( 2023 ); Tonmoy et al. ( 2024 ) .

Our work builds upon the principles of RAG, where we retrieve the relevant papers based on the query and augment them as context for generating the literature review. This also allows the system to be grounded in the retrieved information and be updated with the latest research where the training data limits the parametric knowledge of the LLM. Figure 6 shows our system’s prompt for effective Retrieval Augmented Generation (RAG).

3.3.2 Plan based generation

To get the best results from LLM, recent research shifts focus on designing better prompts (Prompt Engineering) including 0-shot chain-of-thought prompting   Kojima et al. ( 2022 ); Zhou et al. ( 2022 ) , few-shot prompting   Brown et al. ( 2020 ) techniques, few-shot Chain-of-thought prompting   Wei et al. ( 2022 ) and in-context prompting   Li and Liang ( 2021 ); Qin and Eisner ( 2021 ) . However, the longer context of our problem statement (query paper and multiple relevant papers) hinders the application of these techniques for response generation.

We utilized sentence plan-based prompting techniques drawing upon insights from the literature of traditional modular Natural Language Generation (NLG) pipelines with intermediary steps of sentence planning and surface realization  Reiter and Dale ( 1997 ); Stent et al. ( 2004 ) . These plans provide a sentence structure of the expected output, which efficiently guides the LLM in generating the literature review in a controllable fashion as demonstrated in concurrent work (Agarwal et al., 2024 ) . Figure  7 (in Appendix) shows the prompt for plan-based generation with an example template as:

Please generate {num_sentences} sentences in {num_words} words. Cite {cite_x} at line {line_x}. Cite {cite_y} at line {line_y}.

4 Implementation Details

We build our system using Gradio  Abid et al. ( 2019 ) , which provides a nice interface to quickly and efficiently build system demos. Our user interface is also available at HuggingFace Space 5 5 5 https://huggingface.co/spaces/shubhamagarwal92/LitLLM . We query the Semantic Scholar API available through the Semantic Scholar Open Data Platform (Lo et al., 2020 ; Kinney et al., 2023 ) to search for the relevant papers. Specifically, we use the Academic Graph 6 6 6 https://api.semanticscholar.org/api-docs/graph and Recommendations 7 7 7 https://api.semanticscholar.org/api-docs/recommendations API endpoint. In this work, we use OpenAI API 8 8 8 https://platform.openai.com/docs/guides/gpt to generate results for LLM using GPT-3.5-turbo and GPT-4 model. At the same time, our modular pipeline allows using any LLM (proprietary or open-sourced) for different components. We also allow the end-user to sort the retrieved papers by relevance (default S2 results), citation count, or year.

5 User Experience

As a preliminary study, we provided access to our user interface to 5 different researchers who worked through the demo to write literature reviews and validate the system’s efficacy. We also provide an example in the demo with an abstract for a quick start. Particularly, the users found the 0-shot generation to be more informative about the literature in general while the plan-based generation to be more accessible and tailored for their research paper, as also evident in our demo video. 9 9 9 https://youtu.be/E2ggOZBAFw0 . Table 1 (in Appendix) shows the output-related work for a recent paper  Li et al. ( 2023 ) that was randomly chosen with a number of cited papers as 4. Our system generated an informative query Multimodal Research: Image-Text Model Interaction and retrieved relevant papers where the top recommended paper was also cited in the original paper. While zero-shot generation provides valuable insights into existing literature, plan-based generation produces a more succinct and readily usable literature review.

6 Conclusion and Future Work

In this work, we introduce and describe LitLLM, a system which can generate literature reviews in a few clicks from an abstract using off-the-shelf LLMs. This LLM-powered toolkit relies on the RAG with a re-ranking strategy to generate a literature review with attribution. Our auxiliary tool allows researchers to actively search for related work based on a preliminary research idea, research proposal or even a full abstract. We present a modular pipeline that can be easily adapted to include the next generation of LLMs and other domains, such as news, by changing the source of retrieval information.

Given the growing impact of different LLM-based writing assistants, we are optimistic that our system may aid researchers in searching relevant papers and improve the quality of automatically generated related work sections of a paper. While our system shows promise as a helpful research assistant, we believe that their usage should be disclosed to the readers, and authors should also observe caution in eliminating any possible hallucinations.

In the future, we would also like to explore academic search through multiple APIs, such as Google Scholar. This work only considered abstracts of the query paper and the retrieved papers, which creates a bottleneck in effective literature review generation. With the advent of longer context LLMs, we envision our system ingesting the whole paper (potentially leveraging an efficient LLM-based PDF parser) to provide a more relevant background of the related research. We consider our approach as an initial step for building intelligent research assistants which could help academicians through an interactive setting (Dwivedi-Yu et al., 2022 ) .

• Abid et al. (2019) Abubakar Abid, Ali Abdalla, Ali Abid, Dawood Khan, Abdulrahman Alfozan, and James Zou. 2019. Gradio: Hassle-free sharing and testing of ml models in the wild . arXiv preprint arXiv:1906.02569 .
• Agarwal et al. (2024) Shubham Agarwal, Issam Laradji, Laurent Charlin, and Christopher Pal. 2024. LLMs for Literature Review generation: Are we there yet? Under submission .
• Athaluri et al. (2023) Sai Anirudh Athaluri, Sandeep Varma Manthena, V S R Krishna Manoj Kesapragada, Vineel Yarlagadda, Tirth Dave, and Rama Tulasi Siri Duddumpudi. 2023. Exploring the boundaries of reality: Investigating the phenomenon of artificial intelligence hallucination in scientific writing through chatgpt references . Cureus , 15.
• Brown et al. (2020) Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners .
• Crispino et al. (2023) Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, and Chenguang Wang. 2023. Agent instructs large language models to be general zero-shot reasoners . ArXiv , abs/2310.03710.
• Dwivedi-Yu et al. (2022) Jane Dwivedi-Yu, Timo Schick, Zhengbao Jiang, Maria Lomeli, Patrick Lewis, Gautier Izacard, Edouard Grave, Sebastian Riedel, and Fabio Petroni. 2022. Editeval: An instruction-based benchmark for text improvements. arXiv preprint arXiv:2209.13331 .
• Gao et al. (2023) Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey . arXiv preprint arXiv:2312.10997 .
• Haman and Školník (2023) Michael Haman and Milan Školník. 2023. Using chatgpt to conduct a literature review. Accountability in Research , pages 1–3.
• Hou et al. (2023) Yupeng Hou, Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Wayne Xin Zhao. 2023. Large language models are zero-shot rankers for recommender systems . ArXiv , abs/2305.08845.
• Huang and Tan (2023) Jingshan Huang and Ming Tan. 2023. The role of chatgpt in scientific communication: writing better scientific review articles . American Journal of Cancer Research , 13(4):1148.
• Huang et al. (2023) Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2023. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions . arXiv preprint arXiv:2311.05232 .
• Kim et al. (2020) Jihyeok Kim, Seungtaek Choi, Reinald Kim Amplayo, and Seung-won Hwang. 2020. Retrieval-augmented controllable review generation. In Proceedings of the 28th International Conference on Computational Linguistics , pages 2284–2295.
• Kinney et al. (2023) Rodney Kinney, Chloe Anastasiades, Russell Authur, Iz Beltagy, Jonathan Bragg, Alexandra Buraczynski, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Arman Cohan, et al. 2023. The semantic scholar open data platform. arXiv preprint arXiv:2301.10140 .
• Kojima et al. (2022) Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems , 35:22199–22213.
• Lewis et al. (2020) Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems , 33:9459–9474.
• Li et al. (2023) Hang Li, Jindong Gu, Rajat Koner, Sahand Sharifzadeh, and Volker Tresp. 2023. Do dall-e and flamingo understand each other? In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 1999–2010.
• Li et al. (2022) Junlong Li, Zhuosheng Zhang, and Hai Zhao. 2022. Self-prompting large language models for zero-shot open-domain qa .
• Li et al. (2024) Junyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2024. The dawn after the dark: An empirical study on factuality hallucination in large language models. arXiv preprint arXiv:2401.03205 .
• Li and Liang (2021) Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 .
• Liu et al. (2020) Shangqing Liu, Yu Chen, Xiaofei Xie, Jingkai Siow, and Yang Liu. 2020. Retrieval-augmented generation for code summarization via hybrid gnn. arXiv preprint arXiv:2006.05405 .
• Liusie et al. (2023) Adian Liusie, Potsawee Manakul, and Mark John Francis Gales. 2023. Llm comparative assessment: Zero-shot nlg evaluation through pairwise comparisons using large language models .
• Lo et al. (2020) Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney, and Daniel Weld. 2020. S2ORC: The semantic scholar open research corpus . In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages 4969–4983, Online. Association for Computational Linguistics.
• Lu et al. (2020) Yao Lu, Yue Dong, and Laurent Charlin. 2020. Multi-XScience: A large-scale dataset for extreme multi-document summarization of scientific articles . In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages 8068–8074. Association for Computational Linguistics.
• Ma et al. (2023) Xueguang Ma, Xinyu Zhang, Ronak Pradeep, and Jimmy Lin. 2023. Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156 .
• Parvez et al. (2021) Md Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Retrieval augmented code generation and summarization. arXiv preprint arXiv:2108.11601 .
• Pradeep et al. (2023a) Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023a. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 .
• Pradeep et al. (2023b) Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023b. Rankzephyr: Effective and robust zero-shot listwise reranking is a breeze! arXiv preprint arXiv:2312.02724 .
• Qin and Eisner (2021) Guanghui Qin and Jason Eisner. 2021. Learning how to ask: Querying LMs with mixtures of soft prompts . arXiv preprint arXiv:2104.06599 .
• Qu et al. (2021) Leigang Qu, Meng Liu, Jianlong Wu, Zan Gao, and Liqiang Nie. 2021. Dynamic modality interaction modeling for image-text retrieval . Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval .
• Reiter and Dale (1997) Ehud Reiter and Robert Dale. 1997. Building applied natural language generation systems. Natural Language Engineering , 3(1):57–87.
• Shi et al. (2023) Fobo Shi, Peijun Qing, D. Yang, Nan Wang, Youbo Lei, H. Lu, and Xiaodong Lin. 2023. Prompt space optimizing few-shot reasoning success with large language models . ArXiv , abs/2306.03799.
• Srinivasan et al. (2021) Krishna Srinivasan, Karthik Raman, Jiecao Chen, Michael Bendersky, and Marc Najork. 2021. Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning . Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval .
• Stent et al. (2004) Amanda Stent, Rashmi Prasad, and Marilyn Walker. 2004. Trainable sentence planning for complex information presentations in spoken dialog systems . In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04) , pages 79–86, Barcelona, Spain.
• Sun et al. (2023) Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542 .
• Taylor et al. (2022) Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A large language model for science . arXiv preprint arXiv:2211.09085 .
• Thulke et al. (2021) David Thulke, Nico Daheim, Christian Dugast, and Hermann Ney. 2021. Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog . arXiv preprint arXiv:2102.04643 .
• Tonmoy et al. (2024) SM Tonmoy, SM Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. 2024. A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313 .
• Wei et al. (2021) Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2021. Finetuned language models are zero-shot learners . ArXiv , abs/2109.01652.
• Wei et al. (2022) Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed H Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems .
• Yu et al. (2022) Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models . Trans. Mach. Learn. Res. , 2022.
• Zhang et al. (2023) Xinyu Zhang, Sebastian Hofstätter, Patrick Lewis, Raphael Tang, and Jimmy Lin. 2023. Rank-without-gpt: Building gpt-independent listwise rerankers on open-source large language models. arXiv preprint arXiv:2312.02969 .
• Zhao et al. (2022) Zijia Zhao, Longteng Guo, Xingjian He, Shuai Shao, Zehuan Yuan, and Jing Liu. 2022. Mamo: Fine-grained vision-language representations learning with masked multimodal modeling . Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval .
• Zhou et al. (2022) Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910 .
• Zhu et al. (2023) Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey . arXiv preprint arXiv:2308.07107 .

In the following, we provide snippets of code to retrieve results from the Semantic Scholar API for both recommendation and query-based search:

• 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: Apr 23, 2024 10:51 AM
• URL: https://tamu.libguides.com/c.php?g=1289555

Free Online Literature Review Generator

It’s free and easy to use. A simple upload of your content and your Literature Reviews are autogenerated.

Create Literature Reviews by repurposing audio or video content

The AI works fully automated

No prompt engineering required

Experience the power of AI without needing prompts

Train your AI to exactly sound like you

You can train your AI on a piece of content of yours

Autogenerate Literature Reviews

Create Literature Reviews based on the best templates from top-marketers. You will get your insights in the best format possible.

Extracted from your existing content

Work with your team, edit and download Literature Reviews

Literature Reviews that sound like you

You can train your Free Online Literature Review Generator to sound like you, so you Literature Reviews are always in your own tone and style—the opposite of generating generic-sounding content out of thin air.

AI-based content repurposing for your Literature Reviews

Creating Literature Reviews is part of every good content marketing strategy. And now it has become even more accessible with Free Online Literature Review Generator.

The best Free Online Literature Review Generator.

Create Literature Reviews based on your insights, and that sounds like you inside Unifire, thanks to all the Free Online Literature Review Generator’s unique AI-powered features.

Your content is generated based on the best creator templates and hook frameworks.

Collaboration

Unifire is built for collaboration. Live editing, unlimited team members and workspaces included.

Train your AI

AI’s that can sound like you and learn your own writing style. From vocabulary to sentence structure.

What are Literature Reviews?

Literature reviews are critical assessments of existing research on a specific topic. They synthesize key findings, identify trends, and highlight gaps in the literature, guiding future research directions and informing readers about the current state of knowledge.

How to use the Free Online Literature Review Generator

It couldn’t be easier: Upload a piece of content, audio or video. Let the tool transcribe it and produce your Literature Reviews.

You can upload audio & video files, directly or via a link. After 2-4 mins you will receive your transcript. Autogenerated.

Auto transcription

We have the best transcription running in the background. 97% accuracy on even the most technical topics speaks for itself.

Edit your transcription

No AI is 100% perfect. So, we let you edit your transcript before hitting the generate content button.

Autogeneration

Free Online Literature Review Generator automatically generates your Literature Reviews, based on the best templates we could find. So your content is in the best shape when you get it.

Edit & Collaborate

Free Online Literature Review Generator is entirely collaborative and comes with unlimited team seats, workspaces and a full collaborative suite.

Once you’re ready to distribute, simply copy & paste your content into your favourite tools.

Questions about the Free Online Literature Review Generator

It’s free for your first upload. You get 900 credits every month for free to use.

This is dependent on the length of your upload. If you upload 5 hours it will create much more content than if you upload only 5 mins.

Yes, you can train the AI to adopt your own tone & style. This includes sentence structures, vocabulary and more.

Some of the best Free Online Literature Review Generator include Jasper, Reword, Anyword, and others.

LinkedIn Keyword Generator for creating perfect LinkedIn Keywords

Ai text enhancer for creating perfect ai texts, ai tweet generator for creating perfect tweets, episode title generator for creating perfect episode titles, intro writer for creating perfect intros, image description generator for creating perfect descriptions, twitter tweet generator for creating perfect tweets, carousel ai generator for creating perfect carousels, youtube tags extractor for creating perfect youtube tags, ai book editing software for creating perfect books, your literature reviews deserve to be perfect, and so does the rest of your content.

Repurpose and scale content whether you are a seasoned marketer or a total novice.

RRL Generator - Review of Related Literature

Ai-powered literature review generator.

• Research projects: Generate a comprehensive literature review for your research project, saving time and effort on finding and analyzing relevant resources.
• Academic papers: Create a literature review section for your academic paper that summarizes and analyzes the existing literature on your topic.
• Thesis or dissertation: Develop a literature review chapter for your thesis or dissertation that provides a comprehensive overview of the existing research on your topic.
• Grant proposals: Include a literature review in your grant proposal that demonstrates your understanding of the existing research in your field.

New & Trending Tools

Book review generator, writing examples generator, ai scrambler.

How To Write An A-Grade Literature Review

3 straightforward steps (with examples) + free template.

By: Derek Jansen (MBA) | Expert Reviewed By: Dr. Eunice Rautenbach | October 2019

Quality research is about building onto the existing work of others , “standing on the shoulders of giants”, as Newton put it. The literature review chapter of your dissertation, thesis or research project is where you synthesise this prior work and lay the theoretical foundation for your own research.

Long story short, this chapter is a pretty big deal, which is why you want to make sure you get it right . In this post, I’ll show you exactly how to write a literature review in three straightforward steps, so you can conquer this vital chapter (the smart way).

Overview: The Literature Review Process

• Understanding the “ why “
• Finding the relevant literature
• Cataloguing and synthesising the information
• Outlining & writing up your literature review
• Example of a literature review

But first, the “why”…

Before we unpack how to write the literature review chapter, we’ve got to look at the why . To put it bluntly, if you don’t understand the function and purpose of the literature review process, there’s no way you can pull it off well. So, what exactly is the purpose of the literature review?

Well, there are (at least) four core functions:

• For you to gain an understanding (and demonstrate this understanding) of where the research is at currently, what the key arguments and disagreements are.
• For you to identify the gap(s) in the literature and then use this as justification for your own research topic.
• To help you build a conceptual framework for empirical testing (if applicable to your research topic).
• To inform your methodological choices and help you source tried and tested questionnaires (for interviews ) and measurement instruments (for surveys ).

Most students understand the first point but don’t give any thought to the rest. To get the most from the literature review process, you must keep all four points front of mind as you review the literature (more on this shortly), or you’ll land up with a wonky foundation.

Okay – with the why out the way, let’s move on to the how . As mentioned above, writing your literature review is a process, which I’ll break down into three steps:

• Finding the most suitable literature
• Understanding , distilling and organising the literature
• Planning and writing up your literature review chapter

Importantly, you must complete steps one and two before you start writing up your chapter. I know it’s very tempting, but don’t try to kill two birds with one stone and write as you read. You’ll invariably end up wasting huge amounts of time re-writing and re-shaping, or you’ll just land up with a disjointed, hard-to-digest mess . Instead, you need to read first and distil the information, then plan and execute the writing.

Step 1: Find the relevant literature

Naturally, the first step in the literature review journey is to hunt down the existing research that’s relevant to your topic. While you probably already have a decent base of this from your research proposal , you need to expand on this substantially in the dissertation or thesis itself.

Essentially, you need to be looking for any existing literature that potentially helps you answer your research question (or develop it, if that’s not yet pinned down). There are numerous ways to find relevant literature, but I’ll cover my top four tactics here. I’d suggest combining all four methods to ensure that nothing slips past you:

Method 1 – Google Scholar Scrubbing

Google’s academic search engine, Google Scholar , is a great starting point as it provides a good high-level view of the relevant journal articles for whatever keyword you throw at it. Most valuably, it tells you how many times each article has been cited, which gives you an idea of how credible (or at least, popular) it is. Some articles will be free to access, while others will require an account, which brings us to the next method.

Method 2 – University Database Scrounging

Generally, universities provide students with access to an online library, which provides access to many (but not all) of the major journals.

So, if you find an article using Google Scholar that requires paid access (which is quite likely), search for that article in your university’s database – if it’s listed there, you’ll have access. Note that, generally, the search engine capabilities of these databases are poor, so make sure you search for the exact article name, or you might not find it.

Method 3 – Journal Article Snowballing

At the end of every academic journal article, you’ll find a list of references. As with any academic writing, these references are the building blocks of the article, so if the article is relevant to your topic, there’s a good chance a portion of the referenced works will be too. Do a quick scan of the titles and see what seems relevant, then search for the relevant ones in your university’s database.

Method 4 – Dissertation Scavenging

Similar to Method 3 above, you can leverage other students’ dissertations. All you have to do is skim through literature review chapters of existing dissertations related to your topic and you’ll find a gold mine of potential literature. Usually, your university will provide you with access to previous students’ dissertations, but you can also find a much larger selection in the following databases:

• Open Access Theses & Dissertations
• Stanford SearchWorks

Keep in mind that dissertations and theses are not as academically sound as published, peer-reviewed journal articles (because they’re written by students, not professionals), so be sure to check the credibility of any sources you find using this method. You can do this by assessing the citation count of any given article in Google Scholar. If you need help with assessing the credibility of any article, or with finding relevant research in general, you can chat with one of our Research Specialists .

Alright – with a good base of literature firmly under your belt, it’s time to move onto the next step.

Need a helping hand?

Step 2: Log, catalogue and synthesise

Once you’ve built a little treasure trove of articles, it’s time to get reading and start digesting the information – what does it all mean?

While I present steps one and two (hunting and digesting) as sequential, in reality, it’s more of a back-and-forth tango – you’ll read a little , then have an idea, spot a new citation, or a new potential variable, and then go back to searching for articles. This is perfectly natural – through the reading process, your thoughts will develop , new avenues might crop up, and directional adjustments might arise. This is, after all, one of the main purposes of the literature review process (i.e. to familiarise yourself with the current state of research in your field).

As you’re working through your treasure chest, it’s essential that you simultaneously start organising the information. There are three aspects to this:

• Logging reference information
• Building an organised catalogue
• Distilling and synthesising the information

I’ll discuss each of these below:

2.1 – Log the reference information

As you read each article, you should add it to your reference management software. I usually recommend Mendeley for this purpose (see the Mendeley 101 video below), but you can use whichever software you’re comfortable with. Most importantly, make sure you load EVERY article you read into your reference manager, even if it doesn’t seem very relevant at the time.

2.2 – Build an organised catalogue

In the beginning, you might feel confident that you can remember who said what, where, and what their main arguments were. Trust me, you won’t. If you do a thorough review of the relevant literature (as you must!), you’re going to read many, many articles, and it’s simply impossible to remember who said what, when, and in what context . Also, without the bird’s eye view that a catalogue provides, you’ll miss connections between various articles, and have no view of how the research developed over time. Simply put, it’s essential to build your own catalogue of the literature.

I would suggest using Excel to build your catalogue, as it allows you to run filters, colour code and sort – all very useful when your list grows large (which it will). How you lay your spreadsheet out is up to you, but I’d suggest you have the following columns (at minimum):

• Author, date, title – Start with three columns containing this core information. This will make it easy for you to search for titles with certain words, order research by date, or group by author.
• Categories or keywords – You can either create multiple columns, one for each category/theme and then tick the relevant categories, or you can have one column with keywords.
• Key arguments/points – Use this column to succinctly convey the essence of the article, the key arguments and implications thereof for your research.
• Context – Note the socioeconomic context in which the research was undertaken. For example, US-based, respondents aged 25-35, lower- income, etc. This will be useful for making an argument about gaps in the research.
• Methodology – Note which methodology was used and why. Also, note any issues you feel arise due to the methodology. Again, you can use this to make an argument about gaps in the research.
• Quotations – Note down any quoteworthy lines you feel might be useful later.
• Notes – Make notes about anything not already covered. For example, linkages to or disagreements with other theories, questions raised but unanswered, shortcomings or limitations, and so forth.

If you’d like, you can try out our free catalog template here (see screenshot below).

2.3 – Digest and synthesise

Most importantly, as you work through the literature and build your catalogue, you need to synthesise all the information in your own mind – how does it all fit together? Look for links between the various articles and try to develop a bigger picture view of the state of the research. Some important questions to ask yourself are:

• What answers does the existing research provide to my own research questions ?
• Which points do the researchers agree (and disagree) on?
• How has the research developed over time?
• Where do the gaps in the current research lie?

To help you develop a big-picture view and synthesise all the information, you might find mind mapping software such as Freemind useful. Alternatively, if you’re a fan of physical note-taking, investing in a large whiteboard might work for you.

Step 3: Outline and write it up!

Once you’re satisfied that you have digested and distilled all the relevant literature in your mind, it’s time to put pen to paper (or rather, fingers to keyboard). There are two steps here – outlining and writing:

3.1 – Draw up your outline

Having spent so much time reading, it might be tempting to just start writing up without a clear structure in mind. However, it’s critically important to decide on your structure and develop a detailed outline before you write anything. Your literature review chapter needs to present a clear, logical and an easy to follow narrative – and that requires some planning. Don’t try to wing it!

Naturally, you won’t always follow the plan to the letter, but without a detailed outline, you’re more than likely going to end up with a disjointed pile of waffle , and then you’re going to spend a far greater amount of time re-writing, hacking and patching. The adage, “measure twice, cut once” is very suitable here.

In terms of structure, the first decision you’ll have to make is whether you’ll lay out your review thematically (into themes) or chronologically (by date/period). The right choice depends on your topic, research objectives and research questions, which we discuss in this article .

Once that’s decided, you need to draw up an outline of your entire chapter in bullet point format. Try to get as detailed as possible, so that you know exactly what you’ll cover where, how each section will connect to the next, and how your entire argument will develop throughout the chapter. Also, at this stage, it’s a good idea to allocate rough word count limits for each section, so that you can identify word count problems before you’ve spent weeks or months writing!

PS – check out our free literature review chapter template…

3.2 – Get writing

With a detailed outline at your side, it’s time to start writing up (finally!). At this stage, it’s common to feel a bit of writer’s block and find yourself procrastinating under the pressure of finally having to put something on paper. To help with this, remember that the objective of the first draft is not perfection – it’s simply to get your thoughts out of your head and onto paper, after which you can refine them. The structure might change a little, the word count allocations might shift and shuffle, and you might add or remove a section – that’s all okay. Don’t worry about all this on your first draft – just get your thoughts down on paper.

Once you’ve got a full first draft (however rough it may be), step away from it for a day or two (longer if you can) and then come back at it with fresh eyes. Pay particular attention to the flow and narrative – does it fall fit together and flow from one section to another smoothly? Now’s the time to try to improve the linkage from each section to the next, tighten up the writing to be more concise, trim down word count and sand it down into a more digestible read.

Once you’ve done that, give your writing to a friend or colleague who is not a subject matter expert and ask them if they understand the overall discussion. The best way to assess this is to ask them to explain the chapter back to you. This technique will give you a strong indication of which points were clearly communicated and which weren’t. If you’re working with Grad Coach, this is a good time to have your Research Specialist review your chapter.

Finally, tighten it up and send it off to your supervisor for comment. Some might argue that you should be sending your work to your supervisor sooner than this (indeed your university might formally require this), but in my experience, supervisors are extremely short on time (and often patience), so, the more refined your chapter is, the less time they’ll waste on addressing basic issues (which you know about already) and the more time they’ll spend on valuable feedback that will increase your mark-earning potential.

Literature Review Example

In the video below, we unpack an actual literature review so that you can see how all the core components come together in reality.

Let’s Recap

In this post, we’ve covered how to research and write up a high-quality literature review chapter. Let’s do a quick recap of the key takeaways:

• It is essential to understand the WHY of the literature review before you read or write anything. Make sure you understand the 4 core functions of the process.
• The first step is to hunt down the relevant literature . You can do this using Google Scholar, your university database, the snowballing technique and by reviewing other dissertations and theses.
• Next, you need to log all the articles in your reference manager , build your own catalogue of literature and synthesise all the research.
• Following that, you need to develop a detailed outline of your entire chapter – the more detail the better. Don’t start writing without a clear outline (on paper, not in your head!)
• Write up your first draft in rough form – don’t aim for perfection. Remember, done beats perfect.
• Refine your second draft and get a layman’s perspective on it . Then tighten it up and submit it to your supervisor.

Psst… there’s more!

This post is an extract from our bestselling short course, Literature Review Bootcamp . If you want to work smart, you don't want to miss this .

You Might Also Like:

38 Comments

Thank you very much. This page is an eye opener and easy to comprehend.

This is awesome!

I wish I come across GradCoach earlier enough.

But all the same I’ll make use of this opportunity to the fullest.

Thank you for this good job.

Keep it up!

You’re welcome, Yinka. Thank you for the kind words. All the best writing your literature review.

Thank you for a very useful literature review session. Although I am doing most of the steps…it being my first masters an Mphil is a self study and one not sure you are on the right track. I have an amazing supervisor but one also knows they are super busy. So not wanting to bother on the minutae. Thank you.

You’re most welcome, Renee. Good luck with your literature review 🙂

This has been really helpful. Will make full use of it. 🙂

Thank you Gradcoach.

Really agreed. Admirable effort

thank you for this beautiful well explained recap.

Thank you so much for your guide of video and other instructions for the dissertation writing.

It is instrumental. It encouraged me to write a dissertation now.

Thank you the video was great – from someone that knows nothing thankyou

an amazing and very constructive way of presetting a topic, very useful, thanks for the effort,

It is timely

It is very good video of guidance for writing a research proposal and a dissertation. Since I have been watching and reading instructions, I have started my research proposal to write. I appreciate to Mr Jansen hugely.

I learn a lot from your videos. Very comprehensive and detailed.

Thank you for sharing your knowledge. As a research student, you learn better with your learning tips in research

I was really stuck in reading and gathering information but after watching these things are cleared thanks, it is so helpful.

Really helpful, Thank you for the effort in showing such information

This is super helpful thank you very much.

Thank you for this whole literature writing review.You have simplified the process.

I’m so glad I found GradCoach. Excellent information, Clear explanation, and Easy to follow, Many thanks Derek!

You’re welcome, Maithe. Good luck writing your literature review 🙂

Thank you Coach, you have greatly enriched and improved my knowledge

Great piece, so enriching and it is going to help me a great lot in my project and thesis, thanks so much

This is THE BEST site for ANYONE doing a masters or doctorate! Thank you for the sound advice and templates. You rock!

Thanks, Stephanie 🙂

This is mind blowing, the detailed explanation and simplicity is perfect.

I am doing two papers on my final year thesis, and I must stay I feel very confident to face both headlong after reading this article.

thank you so much.

if anyone is to get a paper done on time and in the best way possible, GRADCOACH is certainly the go to area!

This is very good video which is well explained with detailed explanation

Thank you excellent piece of work and great mentoring

Thanks, it was useful

Thank you very much. the video and the information were very helpful.

Good morning scholar. I’m delighted coming to know you even before the commencement of my dissertation which hopefully is expected in not more than six months from now. I would love to engage my study under your guidance from the beginning to the end. I love to know how to do good job

Thank you so much Derek for such useful information on writing up a good literature review. I am at a stage where I need to start writing my one. My proposal was accepted late last year but I honestly did not know where to start

Like the name of your YouTube implies you are GRAD (great,resource person, about dissertation). In short you are smart enough in coaching research work.

This is a very well thought out webpage. Very informative and a great read.

Very timely.

I appreciate.

Very comprehensive and eye opener for me as beginner in postgraduate study. Well explained and easy to understand. Appreciate and good reference in guiding me in my research journey. Thank you

Thank you. I requested to download the free literature review template, however, your website wouldn’t allow me to complete the request or complete a download. May I request that you email me the free template? Thank you.

Submit a Comment 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.

• Print Friendly

JavaScript required

We’re sorry, but Coda doesn’t work properly without JavaScript enabled.

Research Sources Log Research Sources Log

Welcome aboard, how to get started, how to use the template, starting with research sources log, it’s okay if you don’t fill out all of the fields. the more fields filled out, the more accurate the analysis., hint: to view a bigger view of the field. click on the field and click on the “ ⤢ ” icon..

All-in-one Literature Review Software

Start your free trial.

Free MAXQDA trial for Windows and Mac

Your trial will end automatically after 14 days.

MAXQDA The All-in-one Literature Review Software

MAXQDA is the best choice for a comprehensive literature review. It works with a wide range of data types and offers powerful tools for literature review, such as reference management, qualitative, vocabulary, text analysis tools, and more.

Document viewer

Your analysis.

As your all-in-one literature review software, MAXQDA can be used to manage your entire research project. Easily import data from texts, interviews, focus groups, PDFs, web pages, spreadsheets, articles, e-books, and even social media data. Connect the reference management system of your choice with MAXQDA to easily import bibliographic data. Organize your data in groups, link relevant quotes to each other, keep track of your literature summaries, and share and compare work with your team members. Your project file stays flexible and you can expand and refine your category system as you go to suit your research.

Developed by and for researchers – since 1989

Having used several qualitative data analysis software programs, there is no doubt in my mind that MAXQDA has advantages over all the others. In addition to its remarkable analytical features for harnessing data, MAXQDA’s stellar customer service, online tutorials, and global learning community make it a user friendly and top-notch product.

Sally S. Cohen – NYU Rory Meyers College of Nursing

Literature Review is Faster and Smarter with MAXQDA

Easily import your literature review data

With a literature review software like MAXQDA, you can easily import bibliographic data from reference management programs for your literature review. MAXQDA can work with all reference management programs that can export their databases in RIS-format which is a standard format for bibliographic information. Like MAXQDA, these reference managers use project files, containing all collected bibliographic information, such as author, title, links to websites, keywords, abstracts, and other information. In addition, you can easily import the corresponding full texts. Upon import, all documents will be automatically pre-coded to facilitate your literature review at a later stage.

Capture your ideas while analyzing your literature

Great ideas will often occur to you while you’re doing your literature review. Using MAXQDA as your literature review software, you can create memos to store your ideas, such as research questions and objectives, or you can use memos for paraphrasing passages into your own words. By attaching memos like post-it notes to text passages, texts, document groups, images, audio/video clips, and of course codes, you can easily retrieve them at a later stage. Particularly useful for literature reviews are free memos written during the course of work from which passages can be copied and inserted into the final text.

Find concepts important to your generated literature review

When generating a literature review you might need to analyze a large amount of text. Luckily MAXQDA as the #1 literature review software offers Text Search tools that allow you to explore your documents without reading or coding them first. Automatically search for keywords (or dictionaries of keywords), such as important concepts for your literature review, and automatically code them with just a few clicks. Document variables that were automatically created during the import of your bibliographic information can be used for searching and retrieving certain text segments. MAXQDA’s powerful Coding Query allows you to analyze the combination of activated codes in different ways.

Aggregate your literature review

When conducting a literature review you can easily get lost. But with MAXQDA as your literature review software, you will never lose track of the bigger picture. Among other tools, MAXQDA’s overview and summary tables are especially useful for aggregating your literature review results. MAXQDA offers overview tables for almost everything, codes, memos, coded segments, links, and so on. With MAXQDA literature review tools you can create compressed summaries of sources that can be effectively compared and represented, and with just one click you can easily export your overview and summary tables and integrate them into your literature review report.

Powerful and easy-to-use literature review tools

Quantitative aspects can also be relevant when conducting a literature review analysis. Using MAXQDA as your literature review software enables you to employ a vast range of procedures for the quantitative evaluation of your material. You can sort sources according to document variables, compare amounts with frequency tables and charts, and much more. Make sure you don’t miss the word frequency tools of MAXQDA’s add-on module for quantitative content analysis. Included are tools for visual text exploration, content analysis, vocabulary analysis, dictionary-based analysis, and more that facilitate the quantitative analysis of terms and their semantic contexts.

Visualize your literature review

As an all-in-one literature review software, MAXQDA offers a variety of visual tools that are tailor-made for qualitative research and literature reviews. Create stunning visualizations to analyze your material. Of course, you can export your visualizations in various formats to enrich your literature review analysis report. Work with word clouds to explore the central themes of a text and key terms that are used, create charts to easily compare the occurrences of concepts and important keywords, or make use of the graphical representation possibilities of MAXMaps, which in particular permit the creation of concept maps. Thanks to the interactive connection between your visualizations with your MAXQDA data, you’ll never lose sight of the big picture.

AI Assist: literature review software meets AI

AI Assist – your virtual research assistant – supports your literature review with various tools. AI Assist simplifies your work by automatically analyzing and summarizing elements of your research project and by generating suggestions for subcodes. No matter which AI tool you use – you can customize your results to suit your needs.

Free tutorials and guides on literature review

MAXQDA offers a variety of free learning resources for literature review, making it easy for both beginners and advanced users to learn how to use the software. From free video tutorials and webinars to step-by-step guides and sample projects, these resources provide a wealth of information to help you understand the features and functionality of MAXQDA for literature review. For beginners, the software’s user-friendly interface and comprehensive help center make it easy to get started with your data analysis, while advanced users will appreciate the detailed guides and tutorials that cover more complex features and techniques. Whether you’re just starting out or are an experienced researcher, MAXQDA’s free learning resources will help you get the most out of your literature review.

Free MAXQDA Trial for Windows and Mac

Get your maxqda license, compare the features of maxqda and maxqda analytics pro, faq: literature review software.

Literature review software is a tool designed to help researchers efficiently manage and analyze the existing body of literature relevant to their research topic. MAXQDA, a versatile qualitative data analysis tool, can be instrumental in this process.

Literature review software, like MAXQDA, typically includes features such as data import and organization, coding and categorization, advanced search capabilities, data visualization tools, and collaboration features. These features facilitate the systematic review and analysis of relevant literature.

Literature review software, including MAXQDA, can assist in qualitative data interpretation by enabling researchers to organize, code, and categorize relevant literature. This organized data can then be analyzed to identify trends, patterns, and themes, helping researchers draw meaningful insights from the literature they’ve reviewed.

Yes, literature review software like MAXQDA is suitable for researchers of all levels of experience. It offers user-friendly interfaces and extensive support resources, making it accessible to beginners while providing advanced features that cater to the needs of experienced researchers.

Getting started with literature review software, such as MAXQDA, typically involves downloading and installing the software, importing your relevant literature, and exploring the available features. Many software providers offer tutorials and documentation to help users get started quickly.

For students, MAXQDA can be an excellent literature review software choice. Its user-friendly interface, comprehensive feature set, and educational discounts make it a valuable tool for students conducting literature reviews as part of their academic research.

MAXQDA is available for both Windows and Mac users, making it a suitable choice for Mac users looking for literature review software. It offers a consistent and feature-rich experience on Mac operating systems.

When it comes to literature review software, MAXQDA is widely regarded as one of the best choices. Its robust feature set, user-friendly interface, and versatility make it a top pick for researchers conducting literature reviews.

Yes, literature reviews can be conducted without software. However, using literature review software like MAXQDA can significantly streamline and enhance the process by providing tools for efficient data management, analysis, and visualization.

• Literature review tool

The following tool will help you learn how to conduct a solid review of literature. To do so, you will have to answer the questions posed in the form you will find on the lower left side, while checking the resources provided on the right side.

Positionality is the notion that identity , paradigmatic views , and location in time and space influence how one understands the world. Consequently, it is essential to take into account positionality before engaging in research, including research synthesis. Learn more about identity, approaches or paradigmatic views such as positivism, interpretivism, constructivism, and others here

The second step in the generation of the literature review design is setting purposes and objectives that will drive the review process.  Your searching strategies, the literature analysis, and even a review structure depend on the purposes of a review, the same way as the goals and research questions in a research study shape its design. Learn more about the purposes and objectives of a traditional literature "nested" in a research study and a research synthesis.

There are key things to think about before you start searching for literature or conduct research synthesis.  You should define and narrow your topic. Since each disciplinary domain has its own thesaurus, index, and databases,  contemplate in which disciplines or areas of study your research synthesis will be conducted. Formulate the initial research question that you will develop further during the search for the literature and the design step. Learn more here.

The conceptual & theoretical framework of your study is the system of concepts, assumptions, expectations, beliefs, and theories that supports and informs your research. It is a formulation of what you think is going on with what you are studying—a tentative theory of what is happening and why. Read more about "concepts" and how to search for and clarify them, how to find a relevant theory,   here .

Secondary data analysis and review of literature involve collecting and analyzing a vast array of information and sources.  To help you stay focused, your first step should be to develop a research design or a step-by-step plan or a protocol that guides data collection and analysis. Get familiar with different types if the research designs on this page .

As with any research study, the basic purpose of data collection is to create a systematically organized set of materials that will be analyzed or interpreted. Any type of reviews, not only a systematic review,  benefit from applying relatively systematic methods of searching and collecting secondary data. In this part of the guide , I describe sampling methods, instruments (or searching techniques), and organization of sources.

The seventh step regards the selection and definition of the data analysis strategies that will be used in your study, depending on the research approach followed. You can find here resources that might be of help to better understand the way data analysis work. 

After analyzing studies or literature in a depth and the systematic way one should move to the iterative process of exploring, commonalities and contradictions across relevant studies, emergent themes in order to build a theory, frame future research, or creating a final integrated presentation of finding. Find out more here.

Ethical considerations of conducting literature reviews and the issues of quality are not widely discussed in the literature. Consult t his guide where you will find references to work on ethics of conducting systematic reviews, checklists for quality of meta-analysis and research synthesis.

The following AI tools can assist you in step 9 of the process of generating your design:

Google Bard can be used to identify potential ethical principles a researcher could define to ethically conduct a given study.

For instance, we could use the following prompt: What principles could a researcher define to ethically conduct a qualitative case study regarding the long-term impact of competency-based assessment on secondary education students in a secondary school in Marietta (Georgia)?

The following AI tools can assist you in step 8 of the process of generating your design:

Google Bard can be used to identify potential strategies we could implement as researchers to ensure the trustworthiness/validity of a given study.

For instance, we could use the following prompt: What strategies could a researcher use to ensure the trustworthiness qualitative case study regarding the long-term impact of competency-based assessment on secondary education students in a secondary school in Marietta (Georgia).

The following AI tools can assist you in step 7 of the process of generating your design:

AI data analysis is on the rise. For instance,  the AI module of Atlas.ti can be used to analyze qualitative data.

The following AI tools can assist you in step 5 of the process of generating your design:

Consensus could be used to identify research questions that have been used in previously published studies. Consensus is an AI-powered search engine designed to take in research questions, find relevant insights within research papers, and synthesize the results using large language models. It is not a chatbot. Consensus only searches through peer-reviewed scientific research articles to find the most credible insights to your queries.

AI: Google Bard could be used to identify potential questions for a particular research tradition or design.

For instance, we could use the following prompt: Generate examples of research questions that could be used to drive a qualitative case study regarding the long-term impact of competency-based assessment on secondary education students in a secondary school in Marietta (Georgia).

The following AI tools can assist you in step 4 of the process of generating your design:

Google Bard could be used to help users of Hopscotch understand the differences between research traditions for a certain topic.

For instance, we could use the following prompt:   Generate a brief description of the key elements of a qualitative case study research design regarding the long-term impact of competency-based assessment on secondary education students in a secondary school in Marietta (Georgia). To do this, use the following nine steps proposed by the Hopscotch Model:

Step 1: Paradigmatic View of the Researcher

Step 2: Topics & Goals of the Study

Step 3: Conceptual framework of the study

Step 4: Research Design/tradition

Step 5: Research Questions

Step 6: Data Gathering Methods

Step 7: Data Analysis

Step 8: Trustworthiness/Validity

Step 9: Ethics driving the study

The following AI tools can assist you in step 3 of the process of generating your design:

AI: ResearchRabbit is a scholarly publication discovery tool supported by artificial intelligence (AI). The tool is designed to support your research without you switching between searching modes and databases, a process that is time-consuming and often escalates into further citation mining; a truly unpleasant rabbit hole (and that’s what inspired the name ResearchRabbit)

AI: 2Dsearch  is a radical alternative to conventional ‘advanced search’. Instead of entering Boolean strings into one-dimensional search boxes, queries are formulated by manipulating objects on a two-dimensional canvas. This eliminates syntax errors, makes the query semantics more transparent, and offers new ways to collaborate, share, and optimize search strategies and best practices.

Welcome to ResearchRabbit from ResearchRabbit on Vimeo .

The following AI tools can assist you in step 2 of the process of generating your design:

AI: Consensus could be used to assist users in the identification of relevant topics that have been published in peer-reviewed articles. Consensus is an AI-powered search engine designed to take in research questions, find relevant insights within research papers, and synthesize the results using large language models. It is not a chatbot. Consensus only searches through peer-reviewed scientific research articles to find the most credible insights to your queries.

AI: Carrot2 could be used to identify potential research topics. Carrot2  organizes your search results into topics. With an instant overview of what’s available, you will quickly find what you’re looking for.

The following AI tools can assist you in step 1 of the process of generating your design:

You could use Google Bard , Perplexity , or ChatGPT , to ask for the differences between the key wordlviews that a researcher can bring to a given study.

For instance, we could use the following prompt:   What are the defining characteristics of the main worldviews or paradigmatic positioning (positivistic worldviews, post-positivistic worldview; constructivistic worldview; transformative worldview, and; pragmatic worldview) a researcher can bring to a given study?

The following AI tools can assist you in step 6 of the process of generating your design:

We could use Google Bard to develop a draft of a data collection protocol for a given study.

For instance, we could use the following prompt: Generate an interview protocol for students involved in a qualitative case study regarding the long-term impact of competency-based assessment on secondary education students in a secondary school in Marietta (Georgia).

You can use the following AI tools to assist you in the process of generating your design:

Step 1: Paradigmatic View of the Researcher 

AI: You could use Google Bard , Perplexity , or ChatGPT , to ask for the differences between the key wordlviews that a researcher can bring to a given study.  

Step 2: Topics & Goals of the Study

AI: Google Bard could be used to help users of Hopscotch understand the differences between research traditions for a certain topic.  

AI: Consensus could be used to identify research questions that have been used in previously published studies. Consensus is an AI-powered search engine designed to take in research questions, find relevant insights within research papers, and synthesize the results using large language models. It is not a chatbot. Consensus only searches through peer-reviewed scientific research articles to find the most credible insights to your queries.

AI: We could use Google Bard to develop a draft of a data collection protocol for a given study.

AI: We could use the AI module of Atlas.ti to analyze qualitative data

AI: Google Bard could be used to identify potential strategies we could implement as researchers to ensure the trustworthiness/validity of a given study.

AI: Google Bard   could be used to identify potential ethical principles a researcher could define to ethically conduct a given study.

Consensus uses AI to find answers in research papers. You can search for previous research in your field of study that might be helpful to better support the relevance of your research topic and the need to conduct the study that you are proposing. The best way to search is to ask a question.

7 open source tools to make literature reviews easy

Opensource.com

A good literature review is critical for academic research in any field, whether it is for a research article, a critical review for coursework, or a dissertation. In a recent article, I presented detailed steps for doing  a literature review using open source software .

The following is a brief summary of seven free and open source software tools described in that article that will make your next literature review much easier.

1. GNU Linux

Most literature reviews are accomplished by graduate students working in research labs in universities. For absurd reasons, graduate students often have the worst computers on campus. They are often old, slow, and clunky Windows machines that have been discarded and recycled from the undergraduate computer labs. Installing a flavor of GNU Linux will breathe new life into these outdated PCs. There are more than 100 distributions , all of which can be downloaded and installed for free on computers. Most popular Linux distributions come with a "try-before-you-buy" feature. For example, with Ubuntu you can make a bootable USB stick that allows you to test-run the Ubuntu desktop experience without interfering in any way with your PC configuration. If you like the experience, you can use the stick to install Ubuntu on your machine permanently.

Linux distributions generally come with a free web browser, and the most popular is Firefox . Two Firefox plugins that are particularly useful for literature reviews are Unpaywall and Zotero. Keep reading to learn why.

3. Unpaywall

Often one of the hardest parts of a literature review is gaining access to the papers you want to read for your review. The unintended consequence of copyright restrictions and paywalls is it has narrowed access to the peer-reviewed literature to the point that even Harvard University is challenged to pay for it. Fortunately, there are a lot of open access articles—about a third of the literature is free (and the percentage is growing). Unpaywall is a Firefox plugin that enables researchers to click a green tab on the side of the browser and skip the paywall on millions of peer-reviewed journal articles. This makes finding accessible copies of articles much faster that searching each database individually. Unpaywall is fast, free, and legal, as it accesses many of the open access sites that I covered in my paper on using open source in lit reviews .

Formatting references is the most tedious of academic tasks. Zotero can save you from ever doing it again. It operates as an Android app, desktop program, and a Firefox plugin (which I recommend). It is a free, easy-to-use tool to help you collect, organize, cite, and share research. It replaces the functionality of proprietary packages such as RefWorks, Endnote, and Papers for zero cost. Zotero can auto-add bibliographic information directly from websites. In addition, it can scrape bibliographic data from PDF files. Notes can be easily added on each reference. Finally, and most importantly, it can import and export the bibliography databases in all publishers' various formats. With this feature, you can export bibliographic information to paste into a document editor for a paper or thesis—or even to a wiki for dynamic collaborative literature reviews (see tool #7 for more on the value of wikis in lit reviews).

5. LibreOffice

Your thesis or academic article can be written conventionally with the free office suite LibreOffice , which operates similarly to Microsoft's Office products but respects your freedom. Zotero has a word processor plugin to integrate directly with LibreOffice. LibreOffice is more than adequate for the vast majority of academic paper writing.

If LibreOffice is not enough for your layout needs, you can take your paper writing one step further with LaTeX , a high-quality typesetting system specifically designed for producing technical and scientific documentation. LaTeX is particularly useful if your writing has a lot of equations in it. Also, Zotero libraries can be directly exported to BibTeX files for use with LaTeX.

7. MediaWiki

If you want to leverage the open source way to get help with your literature review, you can facilitate a dynamic collaborative literature review . A wiki is a website that allows anyone to add, delete, or revise content directly using a web browser. MediaWiki is free software that enables you to set up your own wikis.

Researchers can (in decreasing order of complexity): 1) set up their own research group wiki with MediaWiki, 2) utilize wikis already established at their universities (e.g., Aalto University ), or 3) use wikis dedicated to areas that they research. For example, several university research groups that focus on sustainability (including mine ) use Appropedia , which is set up for collaborative solutions on sustainability, appropriate technology, poverty reduction, and permaculture.

Using a wiki makes it easy for anyone in the group to keep track of the status of and update literature reviews (both current and older or from other researchers). It also enables multiple members of the group to easily collaborate on a literature review asynchronously. Most importantly, it enables people outside the research group to help make a literature review more complete, accurate, and up-to-date.

Wrapping up

Free and open source software can cover the entire lit review toolchain, meaning there's no need for anyone to use proprietary solutions. Do you use other libre tools for making literature reviews or other academic work easier? Please let us know your favorites in the comments.

Related Content

Systematic Literature Reviews Reinvented

Literature Review by ReadCube introduces a new end-to-end solution for teams tasked with systematically monitoring and analyzing published literature related to your company’s products and discoveries.

Let's discover if ReadCube's Literature Review is the ideal choice for your business.

Next steps: sync an email add-on, schedule a personalized demo to learn more..

Rising Regulatory Requirements & Growing Literature Volume

Systematic literature reviews (SLRs) play a crucial role in assessing therapeutic interventions, but historically have demanded significant investments of time and resources to conduct each review. Most traditional workflows involve coordinating multiple systems in a predominantly manual process.

The era of a thousand clicks is over.

Literature Review by ReadCube is the all-in-one solution that brings each review step together into a single platform, saving your team critical minutes and minimizing the opportunity for error. Not only can it handle the traditional requirements of a regulatory SLR process today, the configurable AI capabilities within ReadCube provide a future-proof platform ready to support organizations in navigating the growing volume of information and increasingly stringent regulatory demands.

Build custom review workflows

• Implement multi-level screening for an in-depth literature review and screening.
• Streamline the review process with your predefined inclusion and exclusion criteria.
• Easily identify, manage, and review any conflicts in data entries when working with multiple reviewers, ensuring alignment and consistency.
• Seamlessly integrate data from past reviews, ensuring continuity and time-saving efficiency.

Depending on your department, industry, and goals, literature reviews vary greatly. ReadCube’s flexible and customizable Literature Review makes it simple for you to design the review that makes the most sense for your team.

Ask the right questions

• Design and manage systematic review forms and questions with ease
• Create subforms, select specific fields, implement conditional hidden fields, and manage shared fields
• Build advanced, calculated fields for enhanced accuracy in data assessment

Design the literature review workflow that actually works for your team with advanced and flexible form builder options.

Share your findings

• Utilize PRISMA for structured reporting and visualization, providing detailed flow diagrams in editable formats.
• Customize exports for reporting - including citation metadata, form data, and custom metadata fields.
• Maintain a detailed audit log of all imports, changes, and identified conflicts, ensuring transparency and traceability.

What’s the point of a review if it’s difficult to share results? Simplified and automatic reporting make it easy to share what you’ve learned - so your organization can make better evidence-based decisions.

Manage your reviews.

• Seamlessly import data using common file types such as RIS, CSV, and nBib from third party databases
• Automatically flag duplicates upon import or manually flag duplicates as part of your review
• Admin dashboards show an overarching view of all projects, with the ability to assign form templates, construct new form templates, delegate reviewers to specific projects, and manage the status of ongoing projects.
• Reviewer dashboards show only the projects and citations relevant to a reviewer’s role. Understand current project status, pinpoint potential conflicts, and seamlessly access reporting features for exclusion, inclusion, and PRISMA.

Ensure your team is on track and making progress with advanced governance features.

From startups to leading global organizations, hundreds of companies trust ReadCube’s award-winning platform to transform the way their team works with scholarly literature.

Request a personalized demo to see what Literature Review can do for your team.