@inproceedings{ye-mitchell-2025-llm,
title = "{LLM} as Entity Disambiguator for Biomedical Entity-Linking",
author = "Ye, Christophe and
Mitchell, Cassie S.",
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.25/",
doi = "10.18653/v1/2025.acl-short.25",
pages = "301--312",
ISBN = "979-8-89176-252-7",
abstract = "Entity linking involves normalizing a mention in medical text to a unique identifier in a knowledge base, such as UMLS or MeSH. Most entity linkers follow a two-stage process: first, a candidate generation step selects high-quality candidates, and then a named entity disambiguation phase determines the best candidate for final linking. This study demonstrates that leveraging a large language model (LLM) as an entity disambiguator significantly enhances entity linking models' accuracy and recall. Specifically, the LLM disambiguator achieves remarkable improvements when applied to alias-matching entity linking methods. Without any fine-tuning, our approach establishes a new state-of-the-art (SOTA), surpassing previous methods on multiple prevalent biomedical datasets by up to 16 points in accuracy. We released our code on GitHub at https://github.com/ChristopheYe/llm{\_}disambiguator"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-mitchell-2025-llm">
<titleInfo>
<title>LLM as Entity Disambiguator for Biomedical Entity-Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassie</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Mitchell</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>Entity linking involves normalizing a mention in medical text to a unique identifier in a knowledge base, such as UMLS or MeSH. Most entity linkers follow a two-stage process: first, a candidate generation step selects high-quality candidates, and then a named entity disambiguation phase determines the best candidate for final linking. This study demonstrates that leveraging a large language model (LLM) as an entity disambiguator significantly enhances entity linking models’ accuracy and recall. Specifically, the LLM disambiguator achieves remarkable improvements when applied to alias-matching entity linking methods. Without any fine-tuning, our approach establishes a new state-of-the-art (SOTA), surpassing previous methods on multiple prevalent biomedical datasets by up to 16 points in accuracy. We released our code on GitHub at https://github.com/ChristopheYe/llm_disambiguator</abstract>
<identifier type="citekey">ye-mitchell-2025-llm</identifier>
<identifier type="doi">10.18653/v1/2025.acl-short.25</identifier>
<location>
<url>https://aclanthology.org/2025.acl-short.25/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>301</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM as Entity Disambiguator for Biomedical Entity-Linking
%A Ye, Christophe
%A Mitchell, Cassie S.
%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 ye-mitchell-2025-llm
%X Entity linking involves normalizing a mention in medical text to a unique identifier in a knowledge base, such as UMLS or MeSH. Most entity linkers follow a two-stage process: first, a candidate generation step selects high-quality candidates, and then a named entity disambiguation phase determines the best candidate for final linking. This study demonstrates that leveraging a large language model (LLM) as an entity disambiguator significantly enhances entity linking models’ accuracy and recall. Specifically, the LLM disambiguator achieves remarkable improvements when applied to alias-matching entity linking methods. Without any fine-tuning, our approach establishes a new state-of-the-art (SOTA), surpassing previous methods on multiple prevalent biomedical datasets by up to 16 points in accuracy. We released our code on GitHub at https://github.com/ChristopheYe/llm_disambiguator
%R 10.18653/v1/2025.acl-short.25
%U https://aclanthology.org/2025.acl-short.25/
%U https://doi.org/10.18653/v1/2025.acl-short.25
%P 301-312
Markdown (Informal)
[LLM as Entity Disambiguator for Biomedical Entity-Linking](https://aclanthology.org/2025.acl-short.25/) (Ye & Mitchell, ACL 2025)
ACL
- Christophe Ye and Cassie S. Mitchell. 2025. LLM as Entity Disambiguator for Biomedical Entity-Linking. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 301–312, Vienna, Austria. Association for Computational Linguistics.