CMMLU: Measuring massive multitask language understanding in Chinese
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Chinese, Benchmark, Multi-task, LLM
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: A comprehensive Chinese assessment suite specifically designed to evaluate the knowledge and reasoning abilities of LLMs within the Chinese language and cultural context.
Abstract: As the capabilities of large language models (LLMs) continue to advance, evaluating their performance is becoming simultaneously 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 60% even, which is the pass mark for Chinese exams. This highlights that there is significant 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 in the Chinese context.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7312
Loading