作者位次 #2/6ACL 2026Findings· Findings of ACL
Pru- C o T : Towards Efficient Reasoning Distillation via Pruning Chain-of-Thought
Han Liu · Shuotian Ma · Hui Li · Xiaotong Zhang · Fenglong Ma · Hong Yu
摘要
Knowledge distillation has emerged as a pivotal paradigm for transferring the superior reasoning capabilities of Large Reasoning Models (LRMs) to efficient student models. However, the raw Chain-of-Thought (CoT) trajectories are often verbose and redundant, which dilutes the underlying logic and...