作者位次 #8/9ACL 2026Poster· Natural Language Processing
Can LLM s Act as Historians? Evaluating Historical Research Capabilities of LLM s via the C hinese Imperial Examination
Lirong Gao · Zeqing Wang · Yuyan Cai · Jiayi Deng · Yanmei Gu · Yiming Zhang · Jia Zhou · Yanfei Zhang · Junbo Zhao
摘要
While Large Language Models (LLMs) have increasingly assisted in historical tasks such as text processing, their capacity for professional-level historical reasoning remains underexplored. Existing benchmarks primarily assess basic knowledge breadth or lexical understanding, failing to capture th...