Language Models Represent Beliefs of Self and Others

作     者：Zhu, Wentao Zhang, Zhining Wang, Yizhou 

作者机构：Center on Frontiers of Computing Studies School of Compter Science Peking University China Inst. for Artificial Intelligence Peking University China Nat'l Eng. Research Center of Visual Technology Peking University China Nat'l Key Lab of General Artificial Intelligence Peking University China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Computational linguistics 

摘      要：Understanding and attributing mental states, known as Theory of Mind (ToM), emerges as a fundamental capability for human social reasoning. While Large Language Models (LLMs) appear to possess certain ToM abilities, the mechanisms underlying these capabilities remain elusive. In this study, we discover that it is possible to linearly decode the belief status from the perspectives of various agents through neural activations of language models, indicating the existence of internal representations of self and others beliefs. By manipulating these representations, we observe dramatic changes in the models ToM performance, underscoring their pivotal role in the social reasoning process. Additionally, our findings extend to diverse social reasoning tasks that involve different causal inference patterns, suggesting the potential generalizability of these representations. © 2024, CC BY-SA.