Interactive active learning for literature screening: finetuning GPT with DeepSeek reasoning for cross-domain generalization
This study introduces an interactive active learning framework that leverages fine-tuned LLMs with reasoning capabilities to enhance literature screening. The approach offers a scalable solution to more efficient and reliable information retrieval in systematic reviews.
Authors
- Y. Lynn Wang (ORCID: https://orcid.org/0000-0003-0773-1212)
- Joseph M. Plasek (ORCID: https://orcid.org/0000-0002-9686-3876)
- Xinsong Du (ORCID: https://orcid.org/0000-0003-3713-3264)
- Peter C. Hou (ORCID: https://orcid.org/0000-0002-7726-2901)
- Yiming Li (ORCID: https://orcid.org/0009-0009-8784-1745)
- Pengyu Hong
- Li Zhou
- Ya-Wen Chuang
- John Lian
- Zhengyang Zhou
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- National Chung Hsing University (TW)
- China Medical University (TW)
- Taichung Veterans General Hospital (TW)
- Brandeis University (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2026-03-03
- DOI
- https://doi.org/10.1093/jamia/ocag014
- Primary Topic
- Machine Learning and Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 0.00