JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Onohara, Shota, Miyai, Atsuyuki, Imajuku, Yuki, Egashira, Kazuki, Baek, Jeonghun, Yue, Xiang, Neubig, Graham, Aizawa, Kiyoharu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909541698895872
author Onohara, Shota
Miyai, Atsuyuki
Imajuku, Yuki
Egashira, Kazuki
Baek, Jeonghun
Yue, Xiang
Neubig, Graham
Aizawa, Kiyoharu
author_facet Onohara, Shota
Miyai, Atsuyuki
Imajuku, Yuki
Egashira, Kazuki
Baek, Jeonghun
Yue, Xiang
Neubig, Graham
Aizawa, Kiyoharu
contents Accelerating research on Large Multimodal Models (LMMs) in non-English languages is crucial for enhancing user experiences across broader populations. In this paper, we introduce JMMMU (Japanese MMMU), the first large-scale Japanese benchmark designed to evaluate LMMs on expert-level tasks based on the Japanese cultural context. To facilitate comprehensive culture-aware evaluation, JMMMU features two complementary subsets: (i) culture-agnostic (CA) subset, where the culture-independent subjects (e.g., Math) are selected and translated into Japanese, enabling one-to-one comparison with its English counterpart MMMU; and (ii) culture-specific (CS) subset, comprising newly crafted subjects that reflect Japanese cultural context. Using the CA subset, we observe performance drop in many LMMs when evaluated in Japanese, which is purely attributable to language variation. Using the CS subset, we reveal their inadequate Japanese cultural understanding. Further, by combining both subsets, we identify that some LMMs perform well on the CA subset but not on the CS subset, exposing a shallow understanding of the Japanese language that lacks depth in cultural understanding. We hope this work will not only help advance LMM performance in Japanese but also serve as a guideline to create high-standard, culturally diverse benchmarks for multilingual LMM development. The project page is https://mmmu-japanese-benchmark.github.io/JMMMU/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17250
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
Onohara, Shota
Miyai, Atsuyuki
Imajuku, Yuki
Egashira, Kazuki
Baek, Jeonghun
Yue, Xiang
Neubig, Graham
Aizawa, Kiyoharu
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Accelerating research on Large Multimodal Models (LMMs) in non-English languages is crucial for enhancing user experiences across broader populations. In this paper, we introduce JMMMU (Japanese MMMU), the first large-scale Japanese benchmark designed to evaluate LMMs on expert-level tasks based on the Japanese cultural context. To facilitate comprehensive culture-aware evaluation, JMMMU features two complementary subsets: (i) culture-agnostic (CA) subset, where the culture-independent subjects (e.g., Math) are selected and translated into Japanese, enabling one-to-one comparison with its English counterpart MMMU; and (ii) culture-specific (CS) subset, comprising newly crafted subjects that reflect Japanese cultural context. Using the CA subset, we observe performance drop in many LMMs when evaluated in Japanese, which is purely attributable to language variation. Using the CS subset, we reveal their inadequate Japanese cultural understanding. Further, by combining both subsets, we identify that some LMMs perform well on the CA subset but not on the CS subset, exposing a shallow understanding of the Japanese language that lacks depth in cultural understanding. We hope this work will not only help advance LMM performance in Japanese but also serve as a guideline to create high-standard, culturally diverse benchmarks for multilingual LMM development. The project page is https://mmmu-japanese-benchmark.github.io/JMMMU/.
title JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.17250