Skip to Main Content

Literature Reviews: AI tools

Using AI tools in reviews

AI powered tools can be helpful at different stages of a review.

Generally speaking, it is best to use these in conjunction with established and validated methods; for example, you could search databases with keywords and then run additional searches with an AI literature searching tool. However, different review methodologies will allow for more or less flexibility of AI use. 

It is always important to assess appropriateness of the tool, understand any bias or weakness, and consider ethical and copyright issues. Before you start using AI tools for your review, make sure you have:

1. Familiarised yourself with the institutional guidance on AI use. You will need to check Aston policy and, if relevant, the assessment guidance provided by your lecturer.

2. Completed a mini course on AI and academic integrity. The Learning Services team, in collaboration with Aston students, have prepared some short online modules to help you use AI responsibly.

3. Checked discipline-specific recommendations. Scroll further down the page to find useful links.

Finally, you can ask the Learning Services team for advice. 

Possible applications of AI tools

  • Developing search strategies

You could ask a GenAI tool like Copilot to suggest synonyms of a keyword and then select the ones that are appropriate. These tools are not capable of developing meaningful search strings or entire strategies, but they can provide more ideas.

  • Screening of results

In systematic reviews and similar methodologies, some AI powered tools can facilitate screening of results. However, the process still needs to be supervised and completed by a human. 

  • Finding additional papers

Database searching has its limitations. Using Ai tools for literature searching  can help you identify additional papers, for example, by finding linked citations. 

Research on AI for reviews

This is a small selection of published research on a topic that is changing rapidly. We encourage you to keep up-to-date with the latest publications.

1. (Clark et al, 2025) 

"Current evidence does not support GenAI use in evidence synthesis without human involvement or oversight. However, for most tasks other than searching, GenAI may have a role in assisting humans with evidence synthesis."

2. (Affengruber et al, 2024)

"For title and abstract screening and literature searching, various evaluated methods and tools are available that aim at improving the efficiency of SR production. However, only few studies have addressed the influence of these methods and tools in real-world workflows."

3. (Khalil et al, 2022)

"The current scoping review identified that LitSuggest, Rayyan, Abstractr, BIBOT, R software, RobotAnalyst, DistillerSR, ExaCT and NetMetaXL have potential to be used for the automation of systematic reviews. However, they are not without limitations."

Selection of AI tools

 

These are some examples of tools covering different aspects of literature reviewing. They all have freemium models. They are not provided by the University, so there isn't specific support available. 

Web-based tool that supports collaborative, efficient screening and selection of studies. 

Answers questions by providing a summary and table of a selection of relevant papers. 

Finds related papers, build citation maps, and track research trends.

General and discipline-specific guidance

 

The following is a selection of guidance available on using AI and GenAI to search for the literature an write reviews. This list is not exhaustive, so please ask Learning Services for advice if you need.

University of Toronto.

International Collaboration for Automation in Systematic Reviews, Cochrane and Campbell, JBI and others)

National Institute for Health and Care Excellence

Cochrane Methods

 

Further resources and support

Need advice? Book an online 1-1 appointment here.

Your Information Specialist can help you with:

  • Clarifying methodologies
  • Advice on appropriate use of AI tools
  • Identifying relevant guidance