Generative AI can be useful at the start of research to quickly gain an overview of a topic and identify gaps in research. It can help you find relevant papers and explore new connections between topics.
It can also be very confidently wrong - it might miss important sources, show bias, or give results that aren’t fully accurate. It’s important to use these tools critically and alongside traditional databases, and to be mindful of how your data is used.
These example videos use the free versions of Copilot and Elicit.
If you have a question you need to answer, but you're struggling to develop a search strategy that finds relevant academic literature, Copilot can help suggest search terms you might use.
Using an "act as" prompt can give you ideas about where to start your reading. If you are new to a field, you can ask the AI to act as a professional in your field and answer your questions about where to look.
Elicit is an AI research assistant. Elicit uses language models to help you automate research workflows, such as undertaking parts of literature reviews.
Elicit can find relevant papers without perfect keyword match, summarize takeaways from the paper[s] specific to your question, and extract key information from the papers. [@elicit-research].
Elicit searches within a limited set of full-text results (Semantic Scholar), although if a DOI is provided in results, you can retrieve full-text from external sources. "Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning." (Elicit Help Centre). Elicit currently has a biomedical focus. (Edinburgh University).
Note:
| Pros | Cons |
|---|---|
| Speeding up the literature review process. | Searches a limited database – Elicit uses Semantic Scholar. However, if a DOI is available, you can often access the full text through other platforms. |
| Automating parts of the evidence-gathering process. | Limited features and easy to hit the paywall in the free version. |
| It works best with studies that report concrete findings. | Not ideal for theoretical or non-empirical research |
Get started with Elicit:
Find help and support:
References
Many thanks to Edinburgh University guidance around Using Generative AI Tools in Academic Work (2025).