作者位次 #3/8ACL 2026Findings· Findings of ACL
Does Theory of Mind Improvement Really Benefit Human- AI Interactions? Empirical Findings from Interactive Evaluations
Nanxu Gong · Zixin Chen · Haotian Li · Zishu Zhao · Jianxun Lian · Huamin Qu · Yanjie Fu · Xing Xie
摘要
Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing benchmarks often measure ToM capability improvement through story-reading, multiple-choice questions from a third-pe...