Harnessing Large‐Language Models for Efficient Data Extraction in Systematic Reviews: The Role of Prompt Engineering
Our findings demonstrate the potential of LLMs, guided by rigorous prompt engineering, to augment the SLR process. However, human oversight remains essential, particularly for complex and nuanced data. As these technologies evolve, continued validation of AI tools will be necessary to ensure accuracy and reliability, and safeguarding of the quality of evidence synthesis.
Authors
- Emma Worthington (ORCID: https://orcid.org/0000-0002-2537-6384)
- Ambar Khan (ORCID: https://orcid.org/0009-0006-0090-2559)
- Emma Boulton
- Sue S. Cross
- Molly Murton (ORCID: https://orcid.org/0000-0002-8853-9400)
- Charlotte Marris (ORCID: https://orcid.org/0000-0001-7555-4452)
- Giuseppina Magri
- David Slater (ORCID: https://orcid.org/0000-0002-3160-0389)
- Swati Kumar
- Elizabeth Lunn
Institutions
- Costello Medical Consulting (United Kingdom) (GB)
Publication Details
- Journal
- Cochrane Evidence Synthesis and Methods
- Published
- 2025-10-27
- DOI
- https://doi.org/10.1002/cesm.70058
- Citations
- 3
- Primary Topic
- Meta-analysis and systematic reviews
- Type
- article
- Field-Weighted Citation Impact
- 4.20