<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-koala">
    <titleInfo>
        <title>KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinyoung</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyeongsoo</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eun</namePart>
        <namePart type="given">Seo</namePart>
        <namePart type="family">Seo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="given">Ho</namePart>
        <namePart type="family">Jang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keunwoo</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seungyoun</namePart>
        <namePart type="family">Shin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ji</namePart>
        <namePart type="given">Won</namePart>
        <namePart type="family">Yoon</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain scarce for non-English languages, with Korean being one such underexplored case. In this paper, we introduce **KoALa-Bench**, a comprehensive benchmark for evaluating Korean speech understanding and speech faithfulness of LALMs. In particular, KoALa-Bench comprises six tasks. Four tasks evaluate fundamental speech understanding capabilities, including automatic speech recognition, speech translation, speech question answering, and speech instruction following, while the remaining two tasks evaluate speech faithfulness, motivated by our observation that several LALMs often fail to fully leverage the speech modality. Furthermore, to reflect Korea-specific knowledge, our benchmark incorporates listening questions from the Korean college scholastic ability test as well as content covering Korean cultural domains. We conduct extensive experiments across six models, including both white-box and black-box ones. Our benchmark, evaluation code, and leaderboard are publicly available at [https://ksbench.github.io/Koala-Bench/](https://ksbench.github.io/Koala-Bench/).</abstract>
    <identifier type="citekey">kim-etal-2026-koala</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.296/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>6807</start>
            <end>6844</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
%A Kim, Jinyoung
%A Lim, Hyeongsoo
%A Seo, Eun Seo
%A Jang, Min Ho
%A Choi, Keunwoo
%A Shin, Seungyoun
%A Yoon, Ji Won
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kim-etal-2026-koala
%X Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain scarce for non-English languages, with Korean being one such underexplored case. In this paper, we introduce **KoALa-Bench**, a comprehensive benchmark for evaluating Korean speech understanding and speech faithfulness of LALMs. In particular, KoALa-Bench comprises six tasks. Four tasks evaluate fundamental speech understanding capabilities, including automatic speech recognition, speech translation, speech question answering, and speech instruction following, while the remaining two tasks evaluate speech faithfulness, motivated by our observation that several LALMs often fail to fully leverage the speech modality. Furthermore, to reflect Korea-specific knowledge, our benchmark incorporates listening questions from the Korean college scholastic ability test as well as content covering Korean cultural domains. We conduct extensive experiments across six models, including both white-box and black-box ones. Our benchmark, evaluation code, and leaderboard are publicly available at [https://ksbench.github.io/Koala-Bench/](https://ksbench.github.io/Koala-Bench/).
%U https://aclanthology.org/2026.emnlp-main.296/
%P 6807-6844

Markdown (Informal)

[KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness](https://aclanthology.org/2026.emnlp-main.296/) (Kim et al., EMNLP 2026)

• KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness (Kim et al., EMNLP 2026)

ACL

• Jinyoung Kim, Hyeongsoo Lim, Eun Seo Seo, Min Ho Jang, Keunwoo Choi, Seungyoun Shin, and Ji Won Yoon. 2026. KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 6807–6844, Budapest, Hungary. Association for Computational Linguistics.