作者位次 #3/6ACL 2026Findings· Findings of ACL
FACT - E : Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning
Yuxi Sun · Aoqi Zuo · Haotian Xie · Wei Gao · Mingming Gong · Jing Ma
摘要
Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps. Existing self-evaluation approaches are prone to inherent biases: the model may confidently endorse coherence even when the step...