作者位次 #4/7ACL 2026Poster· Natural Language Processing
Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process
Tomoki Tsujimura · Matīss Rikters · Masaki Asada · Shusaku Egami · Tatsuya Ishigaki · Ken Yano · Hiroya Takamura
摘要
To reliably interpret the evolving context of an LLM as a reasoning trace, the underlying belief of the LLM needs to transition consistently with the progression of the context.We focus on evaluating whether the beliefs held by a model remain consistent before and after the extension of the conte...