@inproceedings{zhu-etal-2025-trust,
title = "Can We Trust {AI} Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models",
author = "Zhu, Zhihong and
Zhang, Yunyan and
Zhuang, Xianwei and
Zhang, Fan and
Wan, Zhongwei and
Chen, Yuyan and
Long, Qingqing and
Zheng, Yefeng and
Wu, Xian",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.350/",
doi = "10.18653/v1/2025.findings-acl.350",
pages = "6748--6769",
ISBN = "979-8-89176-256-5",
abstract = "Hallucination has emerged as a critical challenge for large language models (LLMs) and large vision-language models (LVLMs), particularly in high-stakes medical applications. Despite its significance, dedicated research on medical hallucination remains unexplored. In this survey, we first provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes. Subsequently, we review recent advancements in detecting, evaluating, and mitigating medical hallucinations, offering a comprehensive overview of evaluation benchmarks, metrics, and strategies developed to tackle this issue. Moreover, we delineate the current challenges and delve into new frontiers, thereby shedding light on future research. We hope this work coupled with open-source resources can provide the community with quick access and spur breakthrough research in medical hallucination."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-trust">
<titleInfo>
<title>Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianwei</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongwei</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingqing</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yefeng</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Wu</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Hallucination has emerged as a critical challenge for large language models (LLMs) and large vision-language models (LVLMs), particularly in high-stakes medical applications. Despite its significance, dedicated research on medical hallucination remains unexplored. In this survey, we first provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes. Subsequently, we review recent advancements in detecting, evaluating, and mitigating medical hallucinations, offering a comprehensive overview of evaluation benchmarks, metrics, and strategies developed to tackle this issue. Moreover, we delineate the current challenges and delve into new frontiers, thereby shedding light on future research. We hope this work coupled with open-source resources can provide the community with quick access and spur breakthrough research in medical hallucination.</abstract>
<identifier type="citekey">zhu-etal-2025-trust</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.350</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.350/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>6748</start>
<end>6769</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models
%A Zhu, Zhihong
%A Zhang, Yunyan
%A Zhuang, Xianwei
%A Zhang, Fan
%A Wan, Zhongwei
%A Chen, Yuyan
%A Long, Qingqing
%A Zheng, Yefeng
%A Wu, Xian
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhu-etal-2025-trust
%X Hallucination has emerged as a critical challenge for large language models (LLMs) and large vision-language models (LVLMs), particularly in high-stakes medical applications. Despite its significance, dedicated research on medical hallucination remains unexplored. In this survey, we first provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes. Subsequently, we review recent advancements in detecting, evaluating, and mitigating medical hallucinations, offering a comprehensive overview of evaluation benchmarks, metrics, and strategies developed to tackle this issue. Moreover, we delineate the current challenges and delve into new frontiers, thereby shedding light on future research. We hope this work coupled with open-source resources can provide the community with quick access and spur breakthrough research in medical hallucination.
%R 10.18653/v1/2025.findings-acl.350
%U https://aclanthology.org/2025.findings-acl.350/
%U https://doi.org/10.18653/v1/2025.findings-acl.350
%P 6748-6769
Markdown (Informal)
[Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models](https://aclanthology.org/2025.findings-acl.350/) (Zhu et al., Findings 2025)
ACL
- Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, Qingqing Long, Yefeng Zheng, and Xian Wu. 2025. Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 6748–6769, Vienna, Austria. Association for Computational Linguistics.