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 length of output. In this paper, we propose SKIP, a self-knowledge-guided…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
