C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

Yuzhen Huang · Yuzhuo Bai · Zhihao Zhu · Junlei Zhang · Jinghan Zhang · Tangjun Su · Junteng Liu · Chuancheng Lv · Yikai Zhang · jiayi lei · Yao Fu · Maosong Sun · Junxian He

Great Hall & Hall B1+B2 (level 1) #325
[ ]
Thu 14 Dec 8:45 a.m. PST — 10:45 a.m. PST


New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requires advanced reasoning abilities to solve. We conduct a comprehensive evaluation of the most advanced LLMs on C-Eval, including both English- and Chinese-oriented models. Results indicate that only GPT-4 could achieve an average accuracy of over 60%, suggesting that there is still significant room for improvement for current LLMs. We anticipate C-Eval will help analyze important strengths and shortcomings of foundation models, and foster their development and growth for Chinese users.

Chat is not available.