Literature Review & Background Research

AI tools can help streamline the early stages of research by finding relevant papers, summarising academic content, and even pointing to gaps in the existing literature. They’re particularly useful when you’re getting familiar with a new topic, developing your research question, or exploring unfamiliar areas. While these tools don’t replace a rigorous, systematic literature review, they can save time and support your background research.

AI can help you:

  • Find relevant papers faster by looking at meaning, not just keywords.
  • Summarise studies and highlight key findings, limitations, and methods.
  • Identify gaps in the literature by comparing many papers at once.
  • Discover related work and visualise how studies are connected.
  • Organise your reading with tools that can “remember” and search through the documents you’ve saved.

Different tools have different strengths, so it’s worth trying a few. Always double-check any AI-generated summaries by reviewing the original papers directly.

 

Tools

Undermind

A researcher-led platform focused on identifying high-quality, relevant papers and ranking based on relevance. Unlike other tools that offer lengthy AI-generated summaries, Undermind keeps summaries short to encourage users to engage with the original papers directly. It’s especially useful when prioritising trustworthy papers and maintaining academic rigour early in the research process.

Perplexity

Perplexity is an AI-powered search tool that generates answers to your questions by searching the internet and providing direct links to the original sources. It’s designed to help you quickly find relevant resources and gain an overview of a topic by synthesising information from multiple sources. Selecting the "Academic" option in the search settings allows you to focus on peer-reviewed papers.

Elicit

Elicit can speed up exploratory (but not systematic) literature reviews. It uses AI to find papers and extract key information (e.g., research questions, findings, limitations) into a user-friendly table. It can also summarise information from PDFs you upload. While powerful, its coverage isn’t as comprehensive as other platforms, such as Undermind. Paid plans allow for more tailored outputs and responses based on more papers.

Scite

Scite helps you quickly understand how a paper is being cited in the academic community. It labels citations as supporting, contrasting, or merely mentioning, and includes short quotes from citing papers alongside direct links. This helps you assess the credibility and influence of a study — useful when you want to understand whether a paper has been well received or critically challenged.

ANARA

Anara AI is an academic research assistant that quickly summarises and organises research papers. It enables efficient note-taking, citation management and collaboration, and highlights connections between sources. Its AI-powered chat and knowledge mapping help researchers extract insights from extensive collections of documents in less time.

NotebookLM 

NotebookLM serves as your personal research assistant, allowing you to upload papers, notes, and links. You can then ask questions based on the material you’ve saved, helping you organise your reading and track key ideas over time. This tool is particularly useful for keeping a structured, searchable knowledge base as you progress through your research, ensuring you don’t lose track of key insights and sources.

The following tools help discover related work to papers you already have and map the research landscapes:

  • Research Rabbit: A free tool that explores how papers are connected through citations. Works well with Zotero.
  • Connected Papers: Visualises related research based on shared references. A good way to explore a topic's “neighbourhood”. Free and paid options.
Note that many of the above tools search Semantic Scholar, a free AI-powered search engine for academic papers. While this has good coverage of academic literature, it is limited to certain publishers (e.g., it excludes Elsevier and Oxford University Press).

This isn’t an exhaustive list of tools; others like Consensus, an AI-powered search engine that summarises academic findings across topics, and SciSpace, which offers paper summaries, explanations, citation tracking, and collaborative features, are also valuable for literature reviews.

 

Further reading & resources

AI Tools for Systematic Literature Reviews

While AI tools can support various stages of the systematic review process, fully automated reviews using tools like Undermind and Elicit are not currently recommended. Traditional methods continue to be advocated for due to the need for rigorous, comprehensive analysis and repeatability. AI tools can be helpful in streamlining certain aspects of the process, but they should complement, not replace manual methods.

This paper overviews the commonly used AI tools in different systematic review processes and discusses opportunities and challenges (domain: health research): Springer - AI Tools in Systematic Reviews

Another general overview on optimising the systematic review process using AI tools: How to Optimize Systematic Reviews with AI

This study explored whether the AI tool Elicit adds value to the systematic review process compared to traditional screening methods, in the context of developing smart living environments for older adults. The study assessed Elicit’s performance across repeatability, reliability, and accuracy. Results varied across repeated searches, with inconsistent findings and missed articles. This suggests that while Elicit can broaden the scope of studies, it currently lacks the consistency and rigour needed to replace traditional methods.

Protocols for comparing AI tools and traditional approaches in systematic reviews are also emerging:

 

AI Tools in Evidence Synthesis - King's College London provides an overview of tools used in developing search strategies, locating relevant articles, and during data screening, extraction, and synthesis.

 

AI Tools specifically for evidence synthesis (non-exhaustive)

  1. Rayyan

    A free, web-based platform designed to expedite the screening and selection process in systematic reviews. Rayyan offers collaborative features, including real-time conflict resolution among reviewers, and supports both web and mobile interfaces.

  2. DistillerSR

    A commercial, web-based application designed to automate all stages of systematic literature reviews. DistillerSR offers features such as AI-assisted screening, customisable workflows, and audit trails to ensure regulatory compliance.

  3. RobotReviewer

    A machine learning system that automates the assessment of risk of bias in randomised controlled trials. RobotReviewer can extract relevant information directly from PDF documents, reducing the need for manual data entry. It assesses some of the risk of bias domains in the Cochrane Risk of Bias Tool and provides supporting information for each judgment.

  4. EPPI-reviewer

    It offers integrated text mining capabilities and specialized visualisation tools, supporting both qualitative and quantitative evidence synthesis. It facilitates various stages of the review process, including screening, data extraction, and synthesis.

This article was published on