一作ACL 2026Findings· Findings of ACL
Valid Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought
Daeyeop Lee · Hwanjo Yu
摘要
Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to “over-reasoning”—the generation of redundant, verbose, or irrelevant steps. While existing reasoning step evaluators e...