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

2026-03-30

arXiv.org

AI Summary

本文通过引入KoALa-Bench，一个针对韩语语音理解及保真度的综合评估基准，解决了大型音频语言模型在非英语语言上缺乏评估标准的问题。

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/Korean-Benchmark/.

Problem

• large audio language models
• Korean speech understanding
• speech faithfulness
• benchmark

Innovation

• large audio language models
• speech understanding
• speech faithfulness
• multilingual evaluation
• Korean-specific knowledge