@inproceedings{li-etal-2024-cmmlu,
title = "{CMMLU}: Measuring massive multitask language understanding in {C}hinese",
author = "Li, Haonan and
Zhang, Yixuan and
Koto, Fajri and
Yang, Yifei and
Zhao, Hai and
Gong, Yeyun and
Duan, Nan and
Baldwin, Timothy",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.671/",
doi = "10.18653/v1/2024.findings-acl.671",
pages = "11260--11285",
abstract = "As the capabilities of large language models (LLMs) continue to advance, evaluating their performance is becoming more important and more challenging. This paper aims to address this issue for Mandarin Chinese in the form of CMMLU, a comprehensive Chinese benchmark that covers various subjects, including natural sciences, social sciences, engineering, and the humanities. We conduct a thorough evaluation of more than 20 contemporary multilingual and Chinese LLMs, assessing their performance across different subjects and settings. The results reveal that most existing LLMs struggle to achieve an accuracy of even 60{\%}, which is the pass mark for Chinese exams. This highlights that there is substantial room for improvement in the capabilities of LLMs. Additionally, we conduct extensive experiments to identify factors impacting the models' performance and propose directions for enhancing LLMs. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models for Chinese."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-cmmlu">
<titleInfo>
<title>CMMLU: Measuring massive multitask language understanding in Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haonan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the capabilities of large language models (LLMs) continue to advance, evaluating their performance is becoming more important and more challenging. This paper aims to address this issue for Mandarin Chinese in the form of CMMLU, a comprehensive Chinese benchmark that covers various subjects, including natural sciences, social sciences, engineering, and the humanities. We conduct a thorough evaluation of more than 20 contemporary multilingual and Chinese LLMs, assessing their performance across different subjects and settings. The results reveal that most existing LLMs struggle to achieve an accuracy of even 60%, which is the pass mark for Chinese exams. This highlights that there is substantial room for improvement in the capabilities of LLMs. Additionally, we conduct extensive experiments to identify factors impacting the models’ performance and propose directions for enhancing LLMs. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models for Chinese.</abstract>
<identifier type="citekey">li-etal-2024-cmmlu</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.671</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.671/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11260</start>
<end>11285</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMMLU: Measuring massive multitask language understanding in Chinese
%A Li, Haonan
%A Zhang, Yixuan
%A Koto, Fajri
%A Yang, Yifei
%A Zhao, Hai
%A Gong, Yeyun
%A Duan, Nan
%A Baldwin, Timothy
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F li-etal-2024-cmmlu
%X As the capabilities of large language models (LLMs) continue to advance, evaluating their performance is becoming more important and more challenging. This paper aims to address this issue for Mandarin Chinese in the form of CMMLU, a comprehensive Chinese benchmark that covers various subjects, including natural sciences, social sciences, engineering, and the humanities. We conduct a thorough evaluation of more than 20 contemporary multilingual and Chinese LLMs, assessing their performance across different subjects and settings. The results reveal that most existing LLMs struggle to achieve an accuracy of even 60%, which is the pass mark for Chinese exams. This highlights that there is substantial room for improvement in the capabilities of LLMs. Additionally, we conduct extensive experiments to identify factors impacting the models’ performance and propose directions for enhancing LLMs. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models for Chinese.
%R 10.18653/v1/2024.findings-acl.671
%U https://aclanthology.org/2024.findings-acl.671/
%U https://doi.org/10.18653/v1/2024.findings-acl.671
%P 11260-11285
Markdown (Informal)
[CMMLU: Measuring massive multitask language understanding in Chinese](https://aclanthology.org/2024.findings-acl.671/) (Li et al., Findings 2024)
ACL
- Haonan Li, Yixuan Zhang, Fajri Koto, Yifei Yang, Hai Zhao, Yeyun Gong, Nan Duan, and Timothy Baldwin. 2024. CMMLU: Measuring massive multitask language understanding in Chinese. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11260–11285, Bangkok, Thailand. Association for Computational Linguistics.