<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-bias">
    <titleInfo>
        <title>Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sheng-Lun</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu-Ling</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yen-Hua</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hen-Hsen</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hsin-Hsi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Recent multimodal large language models (MLLMs) extend language understanding beyond text to speech, enabling unified reasoning across modalities. While biases in text-based LLMs have been widely examined, their persistence and manifestation in spoken inputs remain underexplored. This work presents the first systematic investigation of speech bias in multilingual MLLMs.We construct and release the BiasInEar Dataset, a speech-augmented benchmark based on Global MMLU Lite, spanning English, Chinese, and Korean, balanced by gender and accent, and totaling 70.8 hours (\approx4,249 minutes) of speech with 11,200 questions. Using four complementary metrics (accuracy, entropy, APES, and Fleiss’ ąppa), we evaluate nine representative models under linguistic language and accent, demographic gender, and structural option order perturbations. Our findings reveal that MLLMs are relatively robust to demographic factors but highly sensitive to language and option order, suggesting that speech can amplify existing structural biases. Moreover, architectural design and reasoning strategy substantially affect robustness across languages. Overall, this study establishes a unified framework for assessing fairness and robustness in speech-integrated LLMs, bridging the gap between text- and speech-based evaluation.</abstract>
    <identifier type="citekey">wei-etal-2026-bias</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.80/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1570</start>
            <end>1589</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations
%A Wei, Sheng-Lun
%A Liao, Yu-Ling
%A Chang, Yen-Hua
%A Huang, Hen-Hsen
%A Chen, Hsin-Hsi
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F wei-etal-2026-bias
%X Recent multimodal large language models (MLLMs) extend language understanding beyond text to speech, enabling unified reasoning across modalities. While biases in text-based LLMs have been widely examined, their persistence and manifestation in spoken inputs remain underexplored. This work presents the first systematic investigation of speech bias in multilingual MLLMs.We construct and release the BiasInEar Dataset, a speech-augmented benchmark based on Global MMLU Lite, spanning English, Chinese, and Korean, balanced by gender and accent, and totaling 70.8 hours (\approx4,249 minutes) of speech with 11,200 questions. Using four complementary metrics (accuracy, entropy, APES, and Fleiss’ ąppa), we evaluate nine representative models under linguistic language and accent, demographic gender, and structural option order perturbations. Our findings reveal that MLLMs are relatively robust to demographic factors but highly sensitive to language and option order, suggesting that speech can amplify existing structural biases. Moreover, architectural design and reasoning strategy substantially affect robustness across languages. Overall, this study establishes a unified framework for assessing fairness and robustness in speech-integrated LLMs, bridging the gap between text- and speech-based evaluation.
%U https://aclanthology.org/2026.findings-eacl.80/
%P 1570-1589

Markdown (Informal)

[Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations](https://aclanthology.org/2026.findings-eacl.80/) (Wei et al., Findings 2026)

• Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations (Wei et al., Findings 2026)

ACL

• Sheng-Lun Wei, Yu-Ling Liao, Yen-Hua Chang, Hen-Hsen Huang, and Hsin-Hsi Chen. 2026. Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations. In Findings of the Association for Computational Linguistics: EACL 2026, pages 1570–1589, Rabat, Morocco. Association for Computational Linguistics.