<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hardt-2026-audio">
    <titleInfo>
        <title>Can Audio LLMs Understand Prosodic Focus? An Alternative-Semantics Inference Test with “Only”</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Hardt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>We introduce a new inference test for audio LLMs, where the correct response crucially depends on the location of a focal accent. The proposed task shows for the first time how to test the ability of LLMs to incorporate audio information in truth-conditional semantic interpretation, relying on the theory of alternative semantics. Several native audio models are tested, with performance ranging from random guessing to around 90% accuracy. The task is challenging for all the models tested. A detailed error analysis reveals specific areas of difficulty. The theory of alternative semantics provides a basis for a wide range of systematic tests of audio models.</abstract>
    <identifier type="citekey">hardt-2026-audio</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1884</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1884/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>40166</start>
            <end>40183</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Audio LLMs Understand Prosodic Focus? An Alternative-Semantics Inference Test with “Only”
%A Hardt, Daniel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hardt-2026-audio
%X We introduce a new inference test for audio LLMs, where the correct response crucially depends on the location of a focal accent. The proposed task shows for the first time how to test the ability of LLMs to incorporate audio information in truth-conditional semantic interpretation, relying on the theory of alternative semantics. Several native audio models are tested, with performance ranging from random guessing to around 90% accuracy. The task is challenging for all the models tested. A detailed error analysis reveals specific areas of difficulty. The theory of alternative semantics provides a basis for a wide range of systematic tests of audio models.
%R 10.18653/2026.findings-emnlp.1884
%U https://aclanthology.org/2026.findings-emnlp.1884/
%U https://doi.org/10.18653/2026.findings-emnlp.1884
%P 40166-40183

Markdown (Informal)

[Can Audio LLMs Understand Prosodic Focus? An Alternative-Semantics Inference Test with "Only"](https://aclanthology.org/2026.findings-emnlp.1884/) (Hardt, Findings 2026)

• Can Audio LLMs Understand Prosodic Focus? An Alternative-Semantics Inference Test with “Only” (Hardt, Findings 2026)

ACL

• Daniel Hardt. 2026. Can Audio LLMs Understand Prosodic Focus? An Alternative-Semantics Inference Test with "Only". In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 40166–40183, Budapest, Hungary. Association for Computational Linguistics.