KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Jinyoung, Lim, Hyeongsoo, Seo, Eunseo, Jang, Minho, Choi, Keunwoo, Shin, Seungyoun, Yoon, Ji Won
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915948333629440
author Kim, Jinyoung
Lim, Hyeongsoo
Seo, Eunseo
Jang, Minho
Choi, Keunwoo
Shin, Seungyoun
Yoon, Ji Won
author_facet Kim, Jinyoung
Lim, Hyeongsoo
Seo, Eunseo
Jang, Minho
Choi, Keunwoo
Shin, Seungyoun
Yoon, Ji Won
contents 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/Korean-Benchmark/.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19782
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
Kim, Jinyoung
Lim, Hyeongsoo
Seo, Eunseo
Jang, Minho
Choi, Keunwoo
Shin, Seungyoun
Yoon, Ji Won
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
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/Korean-Benchmark/.
title KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2604.19782