作者位次 #2/8ACL 2026Workshop· Natural Language Processing
Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought
Ryo Mitsuhashi · Gaku Morio · Ayana Niwa · Masahiro Kaneko · Kentaro Inui · Terufumi Morishita · Yuta Koreeda · Yasuhiro Sogawa
摘要
Chain-of-Thought (CoT) in large language models (LLMs) has been widely debated in terms of whether it faithfully reflects an internal reasoning process of models. Parametric faithfulness is a recently proposed metric that uses unlearning to assess whether a model encodes parametric beliefs corres...