作者位次 #4/8ACL 2026Poster· Natural Language Processing
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
Chengzhengxu Li · Xiaoming Liu · Zhaohan Zhang · Shengchao Liu · Guoxin Ma · Yu Lan · Cong Wang · Chao Shen
摘要
Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT in reasoning, which impairs the necessary information for deriving the correc...