KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Nahyun, Son, Guijin, Ko, Hyunwoo, Kim, Chanyoung, An, JunYoung, Han, Kyubeen, Kwak, Il-Youp
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918451775275008
author Lee, Nahyun
Son, Guijin
Ko, Hyunwoo
Kim, Chanyoung
An, JunYoung
Han, Kyubeen
Kwak, Il-Youp
author_facet Lee, Nahyun
Son, Guijin
Ko, Hyunwoo
Kim, Chanyoung
An, JunYoung
Han, Kyubeen
Kwak, Il-Youp
contents We introduce KMMMU, a native Korean benchmark for evaluating multimodal understanding in Korean cultural and institutional settings. KMMMU contains 3,466 questions from exams natively written in Korean, covering nine disciplines and nine visual modality categories, along with a 300-item Korean-specific subset and a hard subset of 627 questions. Unlike translated or English-centric benchmarks, KMMMU targets information-dense problems shaped by local conventions, official standards, and discipline-specific visual formats. Experiments show that the strongest open-source model reaches only 42.05% accuracy on the full set, while the best proprietary model achieves 52.42% on the hard subset. Performance varies across disciplines, with some disciplines emerging as bottlenecks, and Korean-specific questions showing gaps of up to 13.43%. Error analysis suggests that these failures stem less from insufficient reasoning depth than from weak convention-to-label mapping, few-shot symbolic induction, localized knowledge recall, and domain-specific standards understanding. KMMMU provides a testbed for multimodal evaluation beyond English-centric benchmarks and for developing more reliable systems for expert real-world tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13058
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context
Lee, Nahyun
Son, Guijin
Ko, Hyunwoo
Kim, Chanyoung
An, JunYoung
Han, Kyubeen
Kwak, Il-Youp
Computation and Language
Machine Learning
Multimedia
We introduce KMMMU, a native Korean benchmark for evaluating multimodal understanding in Korean cultural and institutional settings. KMMMU contains 3,466 questions from exams natively written in Korean, covering nine disciplines and nine visual modality categories, along with a 300-item Korean-specific subset and a hard subset of 627 questions. Unlike translated or English-centric benchmarks, KMMMU targets information-dense problems shaped by local conventions, official standards, and discipline-specific visual formats. Experiments show that the strongest open-source model reaches only 42.05% accuracy on the full set, while the best proprietary model achieves 52.42% on the hard subset. Performance varies across disciplines, with some disciplines emerging as bottlenecks, and Korean-specific questions showing gaps of up to 13.43%. Error analysis suggests that these failures stem less from insufficient reasoning depth than from weak convention-to-label mapping, few-shot symbolic induction, localized knowledge recall, and domain-specific standards understanding. KMMMU provides a testbed for multimodal evaluation beyond English-centric benchmarks and for developing more reliable systems for expert real-world tasks.
title KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context
topic Computation and Language
Machine Learning
Multimedia
url https://arxiv.org/abs/2604.13058