通过生成时间选择的学生在环链式思维蒸馏
Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection
AI总结：
本文提出Gen-SSD框架，通过生成时间选择提升链式思维蒸馏效果，实验显示其在数学推理基准上优于传统知识蒸馏和其他基线方法。
摘要：
大型推理模型通过长链式思维（CoT）轨迹在复杂任务上表现优异，但直接将此类推理过程转移到小型模型仍具挑战性。关键难点在于并非所有教师生成的推理轨迹都适合学生学习。现有方法通常依赖事后过滤，基于启发式标准在完整生成后选择轨迹。然而，此类方法无法控制生成过程本身，可能仍生成超出学生学习能力的推理路径。为解决这一限制，我们提出Gen-SSD（生成时间自选择蒸馏），一种学生在环框架，进行生成时间选择。学生在教师采样过程中评估候选延续部分，引导仅扩展可学习的推理路径，并使无用分支得以早期修剪。实验表明，Gen-SSD在数学推理基准上优于标准知识蒸馏和最近的基线方法，相比标准KD提升约5.9个百分点，相比其他基线方法最高提升4.7个百分点。进一步分析显示，Gen-SSD生成更稳定和可学习的推理轨迹，突显在生成过程中融入监督对有效蒸馏的重要性。
英文摘要：
Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all teacher-generated reasoning trajectories are suitable for student learning. Existing approaches typically rely on post-hoc filtering, selecting trajectories after full generation based on heuristic criteria. However, such methods cannot control the generation process itself and may still produce reasoning paths that lie outside the student's learning capacity. To address this limitation, we propose Gen-SSD (Generation-time Self-Selection Distillation), a student-in-the-loop framework that performs generation-time selection. Instead of passively consuming complete trajectories, the student evaluates candidate continuations during the teacher's sampling process, guiding the expansion of only learnable reasoning paths and enabling early pruning of unhelpful branches. Experiments on mathematical reasoning benchmarks demonstrate that Gen-SSD consistently outperforms standard knowledge distillation and recent baselines, with improvements of around 5.9 points over Standard KD and up to 4.7 points over other baselines. Further analysis shows that Gen-SSD produces more stable and learnable reasoning trajectories, highlighting the importance of incorporating supervision during generation for effective distillation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
