@inproceedings{born-etal-2026-profiling,
title = "Profiling Hallucinations in Frontier {LLM}s for Entity Linking to Medical Ontologies",
author = "Born, Logan and
Kambhatla, Nishant and
Kubasova, Uliyana and
Siahbani, Maryam and
Vacariu, Andrei and
O{'}Connell, Timothy W. and
Sarkar, Anoop",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.41/",
doi = "10.63317/4zi4vcu7vz4v",
pages = "394--413",
abstract = "The integration of Large Language Models (LLMs) into healthcare promises to revolutionize clinical documentation and interoperability, yet reliability remains a concern. This study presents a comprehensive analysis of hallucinations by frontier LLMs tasked with mapping clinical text to SNOMED CT. Through rigorous experimentation, we identify a critical reliability gap: LLMs hallucinate medical codes at a rate that currently renders them unsuitable for autonomous clinical coding applications. Paradoxically, constraining models to use ground-truth mention spans exacerbates, rather than mitigates, these hallucinations. We further contribute a taxonomy of hallucination types {--} including deprecated codes and cross-ontology errors {--} and demonstrate that general-purpose LLMs significantly underperform compared to specialized zero-shot entity linking approaches. These findings underscore the need for robust verification mechanisms before clinical deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="born-etal-2026-profiling">
<titleInfo>
<title>Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Logan</namePart>
<namePart type="family">Born</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishant</namePart>
<namePart type="family">Kambhatla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uliyana</namePart>
<namePart type="family">Kubasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Siahbani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Vacariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="given">W</namePart>
<namePart type="family">O’Connell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The integration of Large Language Models (LLMs) into healthcare promises to revolutionize clinical documentation and interoperability, yet reliability remains a concern. This study presents a comprehensive analysis of hallucinations by frontier LLMs tasked with mapping clinical text to SNOMED CT. Through rigorous experimentation, we identify a critical reliability gap: LLMs hallucinate medical codes at a rate that currently renders them unsuitable for autonomous clinical coding applications. Paradoxically, constraining models to use ground-truth mention spans exacerbates, rather than mitigates, these hallucinations. We further contribute a taxonomy of hallucination types – including deprecated codes and cross-ontology errors – and demonstrate that general-purpose LLMs significantly underperform compared to specialized zero-shot entity linking approaches. These findings underscore the need for robust verification mechanisms before clinical deployment.</abstract>
<identifier type="citekey">born-etal-2026-profiling</identifier>
<identifier type="doi">10.63317/4zi4vcu7vz4v</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.41/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>394</start>
<end>413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies
%A Born, Logan
%A Kambhatla, Nishant
%A Kubasova, Uliyana
%A Siahbani, Maryam
%A Vacariu, Andrei
%A O’Connell, Timothy W.
%A Sarkar, Anoop
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F born-etal-2026-profiling
%X The integration of Large Language Models (LLMs) into healthcare promises to revolutionize clinical documentation and interoperability, yet reliability remains a concern. This study presents a comprehensive analysis of hallucinations by frontier LLMs tasked with mapping clinical text to SNOMED CT. Through rigorous experimentation, we identify a critical reliability gap: LLMs hallucinate medical codes at a rate that currently renders them unsuitable for autonomous clinical coding applications. Paradoxically, constraining models to use ground-truth mention spans exacerbates, rather than mitigates, these hallucinations. We further contribute a taxonomy of hallucination types – including deprecated codes and cross-ontology errors – and demonstrate that general-purpose LLMs significantly underperform compared to specialized zero-shot entity linking approaches. These findings underscore the need for robust verification mechanisms before clinical deployment.
%R 10.63317/4zi4vcu7vz4v
%U https://aclanthology.org/2026.clinicalnlp-1.41/
%U https://doi.org/10.63317/4zi4vcu7vz4v
%P 394-413
Markdown (Informal)
[Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies](https://aclanthology.org/2026.clinicalnlp-1.41/) (Born et al., ClinicalNLP 2026)
ACL