@inproceedings{roy-roy-2026-towards,
title = "Towards Unified Factuality Evaluation for Biomedical {QA} and Summarization: Aligning Metrics with Clinical Use-Cases",
author = "Roy, Mahule and
Roy, Subhas",
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-1.2/",
pages = "15--19",
ISBN = "979-8-89176-434-7",
abstract = "Large language models achieve strong performance on biomedical question answering and summarization benchmarks, yet traditional evaluation metrics often fail to detect clinically significant factual errors. We introduce a unified evaluation framework that combines reference-based measures with evidence-grounded factuality verification to assess biomedical text generation. Evaluating four open-source models across three benchmarks (BioASQ, PubMedQA, MedLFQA), we find that 13.4?24.7{\%} of generated claims are contradicted and 23?41{\%} are unsupported, despite high lexical overlap scores. Our proposed Fact-Aligned Score (FAS) correlates strongly with claim-level verifiability (rho=0.68), substantially outperforming ROUGE-L (rho=0.41). We release an open-source toolkit with model outputs and analysis scripts to support reproducible factuality evaluation and safer deployment of biomedical LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-roy-2026-towards">
<titleInfo>
<title>Towards Unified Factuality Evaluation for Biomedical QA and Summarization: Aligning Metrics with Clinical Use-Cases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahule</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subhas</namePart>
<namePart type="family">Roy</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>Large language models achieve strong performance on biomedical question answering and summarization benchmarks, yet traditional evaluation metrics often fail to detect clinically significant factual errors. We introduce a unified evaluation framework that combines reference-based measures with evidence-grounded factuality verification to assess biomedical text generation. Evaluating four open-source models across three benchmarks (BioASQ, PubMedQA, MedLFQA), we find that 13.4?24.7% of generated claims are contradicted and 23?41% are unsupported, despite high lexical overlap scores. Our proposed Fact-Aligned Score (FAS) correlates strongly with claim-level verifiability (rho=0.68), substantially outperforming ROUGE-L (rho=0.41). We release an open-source toolkit with model outputs and analysis scripts to support reproducible factuality evaluation and safer deployment of biomedical LLMs.</abstract>
<identifier type="citekey">roy-roy-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.2/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>15</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Unified Factuality Evaluation for Biomedical QA and Summarization: Aligning Metrics with Clinical Use-Cases
%A Roy, Mahule
%A Roy, Subhas
%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 roy-roy-2026-towards
%X Large language models achieve strong performance on biomedical question answering and summarization benchmarks, yet traditional evaluation metrics often fail to detect clinically significant factual errors. We introduce a unified evaluation framework that combines reference-based measures with evidence-grounded factuality verification to assess biomedical text generation. Evaluating four open-source models across three benchmarks (BioASQ, PubMedQA, MedLFQA), we find that 13.4?24.7% of generated claims are contradicted and 23?41% are unsupported, despite high lexical overlap scores. Our proposed Fact-Aligned Score (FAS) correlates strongly with claim-level verifiability (rho=0.68), substantially outperforming ROUGE-L (rho=0.41). We release an open-source toolkit with model outputs and analysis scripts to support reproducible factuality evaluation and safer deployment of biomedical LLMs.
%U https://aclanthology.org/2026.bionlp-1.2/
%P 15-19
Markdown (Informal)
[Towards Unified Factuality Evaluation for Biomedical QA and Summarization: Aligning Metrics with Clinical Use-Cases](https://aclanthology.org/2026.bionlp-1.2/) (Roy & Roy, BioNLP 2026)
ACL