Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning
Yue Wu, Yangmin Huang, Qianyun Du, Lixian Lai, Zhiyang He, Jiaxue Hu, Xiaodong Tao
Abstract
Large language models (LLMs) show potential in healthcare but often generate hallucinations, especially when handling unfamiliar information. In medication, a systematic benchmark to evaluate model capabilities is lacking, which is critical given the high-risk nature of medical information. This paper introduces a Chinese benchmark aimed at assessing models in medication tasks, focusing on knowledge and reasoning across six datasets: indication, dosage and administration, contraindicated population, mechanisms of action, drug recommendation, and drug interaction. We evaluate eight closed-source and five open-source models to identify knowledge boundaries, providing the first systematic analysis of limitations and risks in proprietary medical models.
BibTeX
@inproceedings{wu-etal-2025-believe,
title = "Should {I} Believe in What Medical {AI} Says? A {C}hinese Benchmark for Medication Based on Knowledge and Reasoning",
author = "Wu, Yue and
Huang, Yangmin and
Du, Qianyun and
Lai, Lixian and
He, Zhiyang and
Hu, Jiaxue and
Tao, Xiaodong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.91/",
doi = "10.18653/v1/2025.acl-short.91",
pages = "1155--1164",
ISBN = "979-8-89176-252-7"
}