文章探讨大型语言模型（LLMs）是否具备“心智理论”，即理解自身及他人心理状态的能力。研究通过基准测试评估LLMs在社会推理任务中的表现，并指出GPT-4在特定心智理论测试中超越人类水平。 2025-9-24 15:0:26 Author: hackernoon.com(查看原文) 阅读量:6 收藏
New Story
by We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
byEScholar: Electronic Academic Papers for Scholars@escholar
September 24th, 2025
Audio Presented by
Speed
Voice
byEScholar: Electronic Academic Papers for Scholars@escholar
byEScholar: Electronic Academic Papers for Scholars@escholar
We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
Story's Credibility
byEScholar: Electronic Academic Papers for Scholars@escholar
We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
Story's Credibility
About Author
We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
Comments
TOPICS
Related Stories
如有侵权请联系:admin#unsafe.sh