Data extraction in evidence synthesis is labour-intensive, costly, and prone to errors. The use of large language models (LLMs) presents a promising approach for AI-assisted data extraction, potentially enhancing both efficiency and accuracy.

In this session, part of the Artificial Intelligence (AI) methods in evidence synthesis series, the presenter will give an overview of the current research landscape concerning data extraction using LLMs. The presenter will also show findings from a study within reviews (SWAR) that validated the workflow of employing an LLM for semi-automating data extraction within systematic reviews. Additionally, the webinar will address current methodological challenges in evaluating LLMs for data extraction tasks.

This session is aimed at anyone conducting evidence synthesis.

Presenter Bio

Gerald Gartlehner is a professor for evidence-based medicine and clinical epidemiology and the co-director of Cochrane Austria. He is also a co-convenor of the Cochrane Rapid Review Methods Groups. With over two decades of experience in conducting evidence synthesis, Gartlehner has recently focused on evaluating the performance of LLMs for semi-automating various steps in the evidence synthesis processes.

Sign up

Wednesday, 12 March 2025, 14:00 UTC [check the time in your timezone] SIGN UP HERE

You will need a Cochrane Account to register for this webinar. If you don’t have a Cochrane Account you will be able to register for free on the following page. You will be able to use this account for all future activity. A brief guidance on how to sign up using your Cochrane Account is available here and if you have any problems, please contact support@cochrane.org