A Weighted Voting Approach for Traditional Chinese Medicine Formula Classification Using Large Language Models: Algorithm Development and Validation Study
This study aims to explore the effectiveness of LLMs in the TCM formula classification task. To this end, we propose an ensemble learning method that integrates multiple fine-tuned LLMs through a voting mechanism. This method not only improves classification accuracy but also enhances the existing classification system for classifying the efficacy of TCM formula.
Authors
- Heinrich Herre (ORCID: https://orcid.org/0000-0001-5343-9218)
- Keqian Li (ORCID: https://orcid.org/0009-0002-5956-3038)
- Yan Zhu (ORCID: https://orcid.org/0000-0002-5592-8258)
- Keyu Yao (ORCID: https://orcid.org/0000-0003-2655-9243)
- Suyuan Peng (ORCID: https://orcid.org/0000-0002-8221-7574)
- Zhe Wang (ORCID: https://orcid.org/0009-0000-2387-784X)
- Xiaolin Yang (ORCID: https://orcid.org/0000-0001-9008-6650)
- Hua Liu
Institutions
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Peking Union Medical College Hospital (CN)
- Changchun University of Chinese Medicine (CN)
- China Academy of Chinese Medical Sciences (CN)
- Leipzig University (DE)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-07-24
- DOI
- https://doi.org/10.2196/69286
- Primary Topic
- Traditional Chinese Medicine Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00