@inproceedings{wang-etal-2025-medcite,
title = "{M}ed{C}ite: Can Language Models Generate Verifiable Text for Medicine?",
author = "Wang, Xiao and
Tan, Mengjue and
Jin, Qiao and
Xiong, Guangzhi and
Hu, Yu and
Zhang, Aidong and
Lu, Zhiyong and
Zhang, Minjia",
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.967/",
doi = "10.18653/v1/2025.findings-acl.967",
pages = "18891--18913",
ISBN = "979-8-89176-256-5",
abstract = "Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. In this work, we introduce MedCite, the first end-to-end framework that facilitates the design and evaluation of LLM citations for medical tasks. Meanwhile, we introduce a novel multi-pass retrieval-citation method that generates high-quality citations.Our extensive evaluation highlights the challenges and opportunities of citation generation for medical tasks, while identifying important design choices that have a significant impact on the final citation quality. Our proposed method achieves superior citation precision and recall improvements compared to strong baseline methods, and we show that our evaluation results correlate well with annotation results from professional experts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-medcite">
<titleInfo>
<title>MedCite: Can Language Models Generate Verifiable Text for Medicine?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengjue</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiao</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangzhi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aidong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjia</namePart>
<namePart type="family">Zhang</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>Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. In this work, we introduce MedCite, the first end-to-end framework that facilitates the design and evaluation of LLM citations for medical tasks. Meanwhile, we introduce a novel multi-pass retrieval-citation method that generates high-quality citations.Our extensive evaluation highlights the challenges and opportunities of citation generation for medical tasks, while identifying important design choices that have a significant impact on the final citation quality. Our proposed method achieves superior citation precision and recall improvements compared to strong baseline methods, and we show that our evaluation results correlate well with annotation results from professional experts.</abstract>
<identifier type="citekey">wang-etal-2025-medcite</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.967</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.967/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18891</start>
<end>18913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedCite: Can Language Models Generate Verifiable Text for Medicine?
%A Wang, Xiao
%A Tan, Mengjue
%A Jin, Qiao
%A Xiong, Guangzhi
%A Hu, Yu
%A Zhang, Aidong
%A Lu, Zhiyong
%A Zhang, Minjia
%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 wang-etal-2025-medcite
%X Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. In this work, we introduce MedCite, the first end-to-end framework that facilitates the design and evaluation of LLM citations for medical tasks. Meanwhile, we introduce a novel multi-pass retrieval-citation method that generates high-quality citations.Our extensive evaluation highlights the challenges and opportunities of citation generation for medical tasks, while identifying important design choices that have a significant impact on the final citation quality. Our proposed method achieves superior citation precision and recall improvements compared to strong baseline methods, and we show that our evaluation results correlate well with annotation results from professional experts.
%R 10.18653/v1/2025.findings-acl.967
%U https://aclanthology.org/2025.findings-acl.967/
%U https://doi.org/10.18653/v1/2025.findings-acl.967
%P 18891-18913
Markdown (Informal)
[MedCite: Can Language Models Generate Verifiable Text for Medicine?](https://aclanthology.org/2025.findings-acl.967/) (Wang et al., Findings 2025)
ACL
- Xiao Wang, Mengjue Tan, Qiao Jin, Guangzhi Xiong, Yu Hu, Aidong Zhang, Zhiyong Lu, and Minjia Zhang. 2025. MedCite: Can Language Models Generate Verifiable Text for Medicine?. In Findings of the Association for Computational Linguistics: ACL 2025, pages 18891–18913, Vienna, Austria. Association for Computational Linguistics.