SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning
While Chain-of-Thought (CoT) reasoning has been proven to be effective, it often leads to overthinking, resulting in computational overhead, inference latency, and even degraded performance in large language models (LLMs). Existing concise reasoning frameworks significantly compromise accuracy while compressing the len...
Qin-Hong Lin, Yu-Hao Zhang, Ying-Lun Feng et al.
· 0 citations