Conference proceeding
Collaboration among Multiple Large Language Models for Medical Question Answering
Proceedings (IEEE International Conference on Healthcare Informatics. Online), pp 388-396
18 Jun 2025
Abstract
Empowered by vast internal knowledge reservoir, the new generation of large language models (LLMs) demonstrate untapped potential to tackle medical tasks. However, there is insufficient effort made towards summoning up a synergic effect from multiple LLMs' expertise and background. In this study, we propose a multi-LLM collaboration framework tailored on a medical multiple-choice questions dataset. Through post-hoc analysis on 3 pre-trained LLM participants, our framework is proved to boost all LLMs reasoning ability as well as alleviate their divergence among questions. We also measure an LLM's confidence when it confronts with adversary opinions from other LLMs and observe a concurrence between LLM's confidence and prediction accuracy.
Metrics
4 Record Views
Details
- Title
- Collaboration among Multiple Large Language Models for Medical Question Answering
- Creators
- Kexin Shang - Drexel UniversityChia-Hsuan Chang - Drexel UniversityChristopher C. Yang - Drexel University
- Publication Details
- Proceedings (IEEE International Conference on Healthcare Informatics. Online), pp 388-396
- Conference
- 2025 IEEE 13th International Conference on Healthcare Informatics (Rende, Italy, 18 Jun 2025–21 Jun 2025)
- Publisher
- IEEE
- Grant note
- National Science Foundation (10.13039/100000001)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science (Informatics); College of Computing and Informatics
- Scopus ID
- 2-s2.0-105012748078
- Other Identifier
- 991022065642204721