Using AI-powered Tools for Literature Reviews

Benefits

• Efficiency of literature discovery: in addition to traditional keyword searching, AI technology uses algorithms to discover similar literature via seed papers and citation chains.
• Ease of searching: AI technology allows for searching using natural language. 
• Combination of free web resources and users' subscriptions: some of the listed tools allow users to import sources from referencing software like Zotero and EndNote. 

Limitations

• Limitation of literature coverage: most of the listed tools use Semantic Scholar and open repositories as their data source, which retrieves open access literature and may not include sources behind paywalls.
• Uncertainty of search algorithms and full-text extraction technologies.
• AI does not identify good research or bad research, information can be generated based on poor research containing errors.
• AI systems can inherit biases present in the data they are trained on, which can affect the objectivity and accuracy of the synthesized information
• AI can summarize and organize information, but it often lacks the ability to critically analyze and synthesize complex ideas as a human researcher would.
• Due to the lack of reproducibility and transparency in search processes, generative AI tools can not be used solely for the Systematic Review search stage, but could be beneficial for screening and data extraction purposes.
• AI hallucinations can not be completely avoided at this stage, which conflicts with the evidence-based approach in scientific research and may lead to misleading conclusions.
• The above limitations may affect the comprehensiveness of literature discovered and accuracy of answers generated by these tools.
• Ethical issues including plagiarism and proper attribution of sources

Suggestions

• One of the best practices for using these tools is to find a few quality articles from library databases or MultiSearch (more information on subject databases can be found in subject guides), and use these articles as seed papers for further exploration.
• Always validate the references and check the reputation of the sources, trusted indexing platforms like Google Scholar, Scopus, Web of Science, CrossRef, Library MultiSearch etc. can be used for validating purposes.
• Only use the content generated by AI tools as a starting point and analyse critically, please refer to Macquarie University’s guidance on the responsible use of Generative AI in research and Using Generative Artificial Intelligence Tools at MQ for more information.