@inproceedings{colelough-etal-2026-towards,
title = "Towards Grounded Hallucination Definitions for Biomedical Question Answering with Reproducible Examples from {C}lin{IQL}ink",
author = "Colelough, Brandon and
Bartels, Davis and
Bittner, Madeline and
Demner-Fushman, Dina",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.67/",
pages = "812--842",
ISBN = "979-8-89176-434-7",
abstract = "Hallucinations in biomedical question answering are hard to define and compare because the literature uses overlapping and inconsistent terms. There is currently no grounded definition set that works for biomedical QA, with real examples from open-source LLMs. We introduce a layered definition of hallucinations for biomedical QA, hierarchically structured from the overarching idea of Hallucination in relation to generated model content, to source and consistency orientations, and finally to subtypes. We ground our definition taxonomy in source-attributed literature definitions and reproducible examples from REMOVED FOR REVIEW, where cases can be traced to the question, source passage, generated answer, and annotation record. We provide a framework with annotation, comparison, and error analysis to provide a clearer reference for evidence-grounded biomedical QA. We aim for this example-grounded taxonomy to support automated detection of hallucinations and their potential harmfulness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="colelough-etal-2026-towards">
<titleInfo>
<title>Towards Grounded Hallucination Definitions for Biomedical Question Answering with Reproducible Examples from ClinIQLink</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brandon</namePart>
<namePart type="family">Colelough</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davis</namePart>
<namePart type="family">Bartels</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madeline</namePart>
<namePart type="family">Bittner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>Hallucinations in biomedical question answering are hard to define and compare because the literature uses overlapping and inconsistent terms. There is currently no grounded definition set that works for biomedical QA, with real examples from open-source LLMs. We introduce a layered definition of hallucinations for biomedical QA, hierarchically structured from the overarching idea of Hallucination in relation to generated model content, to source and consistency orientations, and finally to subtypes. We ground our definition taxonomy in source-attributed literature definitions and reproducible examples from REMOVED FOR REVIEW, where cases can be traced to the question, source passage, generated answer, and annotation record. We provide a framework with annotation, comparison, and error analysis to provide a clearer reference for evidence-grounded biomedical QA. We aim for this example-grounded taxonomy to support automated detection of hallucinations and their potential harmfulness.</abstract>
<identifier type="citekey">colelough-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.67/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>812</start>
<end>842</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Grounded Hallucination Definitions for Biomedical Question Answering with Reproducible Examples from ClinIQLink
%A Colelough, Brandon
%A Bartels, Davis
%A Bittner, Madeline
%A Demner-Fushman, Dina
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F colelough-etal-2026-towards
%X Hallucinations in biomedical question answering are hard to define and compare because the literature uses overlapping and inconsistent terms. There is currently no grounded definition set that works for biomedical QA, with real examples from open-source LLMs. We introduce a layered definition of hallucinations for biomedical QA, hierarchically structured from the overarching idea of Hallucination in relation to generated model content, to source and consistency orientations, and finally to subtypes. We ground our definition taxonomy in source-attributed literature definitions and reproducible examples from REMOVED FOR REVIEW, where cases can be traced to the question, source passage, generated answer, and annotation record. We provide a framework with annotation, comparison, and error analysis to provide a clearer reference for evidence-grounded biomedical QA. We aim for this example-grounded taxonomy to support automated detection of hallucinations and their potential harmfulness.
%U https://aclanthology.org/2026.bionlp-1.67/
%P 812-842
Markdown (Informal)
[Towards Grounded Hallucination Definitions for Biomedical Question Answering with Reproducible Examples from ClinIQLink](https://aclanthology.org/2026.bionlp-1.67/) (Colelough et al., BioNLP 2026)
ACL