@inproceedings{kim-etal-2026-clinicast,
title = "{C}lini{CAST}: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage",
author = "Kim, Kyusik and
Yoo, Hyunwoo and
Choi, Jaehoon and
Kim, Kitae and
Rosen, Gail and
Suh, Bongwon",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2056/",
pages = "41321--41343",
ISBN = "979-8-89176-395-1",
abstract = "Recent Large Audio-Language Models (LALMs) integrate acoustic capabilities into reasoning, yet whether they reliably ground clinical judgments in audible evidence remains unproven. We introduce CliniCAST (\textbf{Clini}cal \textbf{C}ontrolled \textbf{A}coustic \textbf{S}ynthetic \textbf{T}riage), a controlled benchmark that disentangles clinically meaningful acoustic cues from lexical content and speaker demographics. CliniCAST comprises 5{,}856 synthetic samples across 12 disease conditions: 4{,}800 audio samples forming 2{,}400 tagged{--}untagged pairs for five-level emergency triage, and 1{,}056 audio{--}text inconsistent samples in which reassuring speech is paired with high-risk acoustic cues. Evaluating a diverse suite of audio-capable foundation models, we find that LALMs exhibit fragile acoustic grounding and a pronounced ``text dominance'' failure mode: reassuring lexical content suppresses response to audible distress signals even under safety-critical conditions. Age and gender interactions are weak across conditions, indicating that the primary failure mode is insufficient cross-modal integration rather than demographic bias. These results suggest current LALMs are not yet robust enough for high-stakes medical triage, and motivate training objectives that explicitly enforce reliance on clinically grounded audible evidence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-clinicast">
<titleInfo>
<title>CliniCAST: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyusik</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunwoo</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehoon</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kitae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gail</namePart>
<namePart type="family">Rosen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bongwon</namePart>
<namePart type="family">Suh</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Recent Large Audio-Language Models (LALMs) integrate acoustic capabilities into reasoning, yet whether they reliably ground clinical judgments in audible evidence remains unproven. We introduce CliniCAST (Clinical Controlled Acoustic Synthetic Triage), a controlled benchmark that disentangles clinically meaningful acoustic cues from lexical content and speaker demographics. CliniCAST comprises 5,856 synthetic samples across 12 disease conditions: 4,800 audio samples forming 2,400 tagged–untagged pairs for five-level emergency triage, and 1,056 audio–text inconsistent samples in which reassuring speech is paired with high-risk acoustic cues. Evaluating a diverse suite of audio-capable foundation models, we find that LALMs exhibit fragile acoustic grounding and a pronounced “text dominance” failure mode: reassuring lexical content suppresses response to audible distress signals even under safety-critical conditions. Age and gender interactions are weak across conditions, indicating that the primary failure mode is insufficient cross-modal integration rather than demographic bias. These results suggest current LALMs are not yet robust enough for high-stakes medical triage, and motivate training objectives that explicitly enforce reliance on clinically grounded audible evidence.</abstract>
<identifier type="citekey">kim-etal-2026-clinicast</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2056/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>41321</start>
<end>41343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CliniCAST: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage
%A Kim, Kyusik
%A Yoo, Hyunwoo
%A Choi, Jaehoon
%A Kim, Kitae
%A Rosen, Gail
%A Suh, Bongwon
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F kim-etal-2026-clinicast
%X Recent Large Audio-Language Models (LALMs) integrate acoustic capabilities into reasoning, yet whether they reliably ground clinical judgments in audible evidence remains unproven. We introduce CliniCAST (Clinical Controlled Acoustic Synthetic Triage), a controlled benchmark that disentangles clinically meaningful acoustic cues from lexical content and speaker demographics. CliniCAST comprises 5,856 synthetic samples across 12 disease conditions: 4,800 audio samples forming 2,400 tagged–untagged pairs for five-level emergency triage, and 1,056 audio–text inconsistent samples in which reassuring speech is paired with high-risk acoustic cues. Evaluating a diverse suite of audio-capable foundation models, we find that LALMs exhibit fragile acoustic grounding and a pronounced “text dominance” failure mode: reassuring lexical content suppresses response to audible distress signals even under safety-critical conditions. Age and gender interactions are weak across conditions, indicating that the primary failure mode is insufficient cross-modal integration rather than demographic bias. These results suggest current LALMs are not yet robust enough for high-stakes medical triage, and motivate training objectives that explicitly enforce reliance on clinically grounded audible evidence.
%U https://aclanthology.org/2026.findings-acl.2056/
%P 41321-41343
Markdown (Informal)
[CliniCAST: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage](https://aclanthology.org/2026.findings-acl.2056/) (Kim et al., Findings 2026)
ACL