@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",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2025-believe">
<titleInfo>
<title>Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangmin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianyun</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixian</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxue</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-252-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">wu-etal-2025-believe</identifier>
<identifier type="doi">10.18653/v1/2025.acl-short.91</identifier>
<location>
<url>https://aclanthology.org/2025.acl-short.91/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1155</start>
<end>1164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning
%A Wu, Yue
%A Huang, Yangmin
%A Du, Qianyun
%A Lai, Lixian
%A He, Zhiyang
%A Hu, Jiaxue
%A Tao, Xiaodong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-252-7
%F wu-etal-2025-believe
%X 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.
%R 10.18653/v1/2025.acl-short.91
%U https://aclanthology.org/2025.acl-short.91/
%U https://doi.org/10.18653/v1/2025.acl-short.91
%P 1155-1164
Markdown (Informal)
[Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning](https://aclanthology.org/2025.acl-short.91/) (Wu et al., ACL 2025)
ACL