Accessibility settings

This paper is in the following e-collection/theme issue:

Artificial Intelligence (AI) in Medical Education (248) Clinical Communication, Electronic Consultation and Telehealth (821) Artificial Intelligence (2437) Generative Language Models Including ChatGPT (871)

Published on in Vol 11 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/70190, first published .
Enhancing Large Language Models for Improved Accuracy and Safety in Medical Question Answering: Comparative Study

Enhancing Large Language Models for Improved Accuracy and Safety in Medical Question Answering: Comparative Study

Enhancing Large Language Models for Improved Accuracy and Safety in Medical Question Answering: Comparative Study

Authors of this article:

Dingqiao Wang1, 2 Author Orcid Image ;   Jinguo Ye1 Author Orcid Image ;   Jingni Li1 Author Orcid Image ;   Jiangbo Liang1 Author Orcid Image ;   Qikai Zhang1 Author Orcid Image ;   Qiuling Hu1 Author Orcid Image ;   Caineng Pan1 Author Orcid Image ;   Dongliang Wang1 Author Orcid Image ;   Zhong Liu1 Author Orcid Image ;   Wen Shi1 Author Orcid Image ;   Mengxiang Guo3 Author Orcid Image ;   Fei Li1 Author Orcid Image ;   Wei Du2 Author Orcid Image ;   Ying-Feng Zheng1 Author Orcid Image
Article Authors Cited by (4) Tweetations Metrics

Journals

  1. Callens S. Effective prompt design for large language models in clinical practice. Acta Clinica Belgica 2026;81(2):118 View
  2. Pawlik L, Deniziak S. Reducing Hallucinations in Medical AI Through Citation Enforced Prompting in RAG Systems. Applied Sciences 2026;16(6):3013 View
  3. Li S, Wang X, Chen Y, Tian M, Lin P, Lai M, Jiang L. Large language models for primary care ophthalmic education: a systematic review. Frontiers in Medicine 2026;13 View
  4. Choi S, Kim D, Jeon J, Kim M, Lee D, Ahn D, Lee E, Kim Y, Youk H. Korean Medical Consultation With Open-Weight Large Language Models: Pilot Comparative Evaluation of Retrieval-Augmented Generation With Metadata Filtering. JMIR Formative Research 2026;10:e72604 View