1
Language Models Encode the Contextual Truth of Propositions
大模型如何在激活空间内编码“上下文真值”？这项研究揭示了线性方向的全新机制，带你深入AI判断真相的内部逻辑。
arXiv:2608.03035v1 Announce Type: new Abstract: Prior work has shown that LLMs encode the truth of factual propositions along linear directions in act…