CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Zheqi, Wu, Xinya, Zhou, Pengfei, Xuan, Richeng, Liu, Guang, Yang, Xi, Zhu, Qiannan, Huang, Hua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911870361796608
author He, Zheqi
Wu, Xinya
Zhou, Pengfei
Xuan, Richeng
Liu, Guang
Yang, Xi
Zhu, Qiannan
Huang, Hua
author_facet He, Zheqi
Wu, Xinya
Zhou, Pengfei
Xuan, Richeng
Liu, Guang
Yang, Xi
Zhu, Qiannan
Huang, Hua
contents Multi-modal large language models(MLLMs) have achieved remarkable progress and demonstrated powerful knowledge comprehension and reasoning abilities. However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge. Current multi-modal benchmarks for domain-specific knowledge concentrate on multiple-choice questions and are predominantly available in English, which imposes limitations on the comprehensiveness of the evaluation. To this end, we introduce CMMU, a novel benchmark for multi-modal and multi-type question understanding and reasoning in Chinese. CMMU consists of 3,603 questions in 7 subjects, covering knowledge from primary to high school. The questions can be categorized into 3 types: multiple-choice, multiple-response, and fill-in-the-blank, bringing greater challenges to MLLMs. In addition, we propose an evaluation strategy called Positional Error Variance for assessing multiple-choice questions. The strategy aims to perform a quantitative analysis of position bias. We evaluate seven open-source MLLMs along with GPT4-V, Gemini-Pro, and Qwen-VL-Plus. The results demonstrate that CMMU poses a significant challenge to the recent MLLMs. The data and code are available at https://github.com/FlagOpen/CMMU.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14011
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning
He, Zheqi
Wu, Xinya
Zhou, Pengfei
Xuan, Richeng
Liu, Guang
Yang, Xi
Zhu, Qiannan
Huang, Hua
Computation and Language
Artificial Intelligence
Multimedia
Multi-modal large language models(MLLMs) have achieved remarkable progress and demonstrated powerful knowledge comprehension and reasoning abilities. However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge. Current multi-modal benchmarks for domain-specific knowledge concentrate on multiple-choice questions and are predominantly available in English, which imposes limitations on the comprehensiveness of the evaluation. To this end, we introduce CMMU, a novel benchmark for multi-modal and multi-type question understanding and reasoning in Chinese. CMMU consists of 3,603 questions in 7 subjects, covering knowledge from primary to high school. The questions can be categorized into 3 types: multiple-choice, multiple-response, and fill-in-the-blank, bringing greater challenges to MLLMs. In addition, we propose an evaluation strategy called Positional Error Variance for assessing multiple-choice questions. The strategy aims to perform a quantitative analysis of position bias. We evaluate seven open-source MLLMs along with GPT4-V, Gemini-Pro, and Qwen-VL-Plus. The results demonstrate that CMMU poses a significant challenge to the recent MLLMs. The data and code are available at https://github.com/FlagOpen/CMMU.
title CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning
topic Computation and Language
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2401.14011