Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies

Logan Born, Nishant Kambhatla, Uliyana Kubasova, Maryam Siahbani, Andrei Vacariu, Timothy W. O’Connell, Anoop Sarkar


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.
Anthology ID:
2026.clinicalnlp-1.41
Volume:
Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Asma Ben Abacha, Steven Bethard, Danielle Bitterman, Tristan Naumann, Kirk Roberts
Venues:
ClinicalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
394–413
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-clinicalnlp-41
DOI:
10.63317/4zi4vcu7vz4v
Bibkey:
Cite (ACL):
Logan Born, Nishant Kambhatla, Uliyana Kubasova, Maryam Siahbani, Andrei Vacariu, Timothy W. O’Connell, and Anoop Sarkar. 2026. Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 394–413, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Profiling Hallucinations in Frontier LLMs for Entity Linking to Medical Ontologies (Born et al., ClinicalNLP 2026)
Copy Citation: