作者位次 #10/17ACL 2026Poster· Natural Language Processing
The G ao Y ao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
Yilun Liu · Chunguang Zhao · Mengyao Piao · Lingqi Miao · Shimin Tao · Minggui HE · Chenxin Liu · Li Zhang · Mahongxia · Jiaxin Guo · Chen Liu · Liqun Deng · Jiansheng Wei · Xiaojun Meng · Fanyi Du · Daimeng Wei · Yanghua Xiao
摘要
Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical limitations: (1) fragmented evaluation dimensions that often neglect deep cultural nuances; (2) insufficient language c...