@inproceedings{chen-etal-2025-medfact,
title = "{M}ed{F}act: A Large-scale {C}hinese Dataset for Evidence-based Medical Fact-checking of {LLM} Responses",
author = "Chen, Tong and
Wang, Zimu and
Miao, Yiyi and
Luo, Haoran and
Yuanfei, Sun and
Wang, Wei and
Jiang, Zhengyong and
Sen, Procheta and
Su, Jionglong",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1646/",
doi = "10.18653/v1/2025.emnlp-main.1646",
pages = "32340--32353",
ISBN = "979-8-89176-332-6",
abstract = "Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored. To address this gap, we introduce MedFact, the first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content. It consists of 1,321 questions and 7,409 claims, mirroring the complexities of real-world medical scenarios. We conduct comprehensive experiments in both in-context learning (ICL) and fine-tuning settings, showcasing the capability and challenges of current LLMs on this task, accompanied by an in-depth error analysis to point out key directions for future research. Our dataset is publicly available at https://github.com/AshleyChenNLP/MedFact."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-medfact">
<titleInfo>
<title>MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyi</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Yuanfei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Procheta</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jionglong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored. To address this gap, we introduce MedFact, the first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content. It consists of 1,321 questions and 7,409 claims, mirroring the complexities of real-world medical scenarios. We conduct comprehensive experiments in both in-context learning (ICL) and fine-tuning settings, showcasing the capability and challenges of current LLMs on this task, accompanied by an in-depth error analysis to point out key directions for future research. Our dataset is publicly available at https://github.com/AshleyChenNLP/MedFact.</abstract>
<identifier type="citekey">chen-etal-2025-medfact</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1646</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1646/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>32340</start>
<end>32353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
%A Chen, Tong
%A Wang, Zimu
%A Miao, Yiyi
%A Luo, Haoran
%A Yuanfei, Sun
%A Wang, Wei
%A Jiang, Zhengyong
%A Sen, Procheta
%A Su, Jionglong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F chen-etal-2025-medfact
%X Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored. To address this gap, we introduce MedFact, the first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content. It consists of 1,321 questions and 7,409 claims, mirroring the complexities of real-world medical scenarios. We conduct comprehensive experiments in both in-context learning (ICL) and fine-tuning settings, showcasing the capability and challenges of current LLMs on this task, accompanied by an in-depth error analysis to point out key directions for future research. Our dataset is publicly available at https://github.com/AshleyChenNLP/MedFact.
%R 10.18653/v1/2025.emnlp-main.1646
%U https://aclanthology.org/2025.emnlp-main.1646/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1646
%P 32340-32353
Markdown (Informal)
[MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses](https://aclanthology.org/2025.emnlp-main.1646/) (Chen et al., EMNLP 2025)
ACL
- Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, and Jionglong Su. 2025. MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 32340–32353, Suzhou, China. Association for Computational Linguistics.