提示：策略内蒸馏中的令牌重要性
TIP: Token Importance in On-Policy Distillation
April 15, 2026
作者: Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang, Alborz Geramifard
cs.AI
摘要
在线策略知识蒸馏（OPD）利用教师模型的令牌级监督，通过学生模型自身产生的交互数据对学生进行训练。并非所有令牌位置都同等重要，但现有对令牌重要性的认知存在局限性。我们直接提出核心问题：在OPKD中哪些令牌携带最有效的学习信号？研究发现，信息量丰富的令牌来源于两个区域：学生模型熵值高的位置，以及学生模型熵值低但师生分歧度高的位置——后者对应学生模型过度自信却判断错误的情形。
实证表明，学生熵是强效的一阶指标：基于熵采样保留50%的令牌进行训练，效果等同或优于全令牌训练，同时峰值内存占用降低达47%。但仅依赖熵会遗漏第二个关键区域。当我们单独提取低熵高分歧令牌时，仅使用不足10%的令牌进行训练即可接近全令牌基线效果，证明过度自信令牌虽在纯熵准则下几乎不可见，却承载着密集的纠错信号。
基于这些发现，我们提出TIP框架（在线策略蒸馏中的令牌重要性），构建以学生熵和师生分歧度为双轴的分层体系，并从理论层面阐释了熵值有效但存在结构局限的原因。该视角催生了结合不确定性与分歧度的类型感知令牌选择机制。我们在Qwen3、Llama和Qwen2.5构成的三个师生模型组合上验证该框架，测试集涵盖MATH-500和AIME 2024/2025，并在长程智能体规划的DeepPlanning基准中实现突破：仅使用不足20%的Q3令牌训练即可超越全令牌OPD效果。实验通过扩展OPD代码库（https://github.com/HJSang/OPSD_OnPolicyDistillation）实现，该库支持有限GPU预算下对大模型进行内存高效的蒸馏训练。
English
On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views of token importance are incomplete. We ask a direct question: which tokens carry the most useful learning signal in OPD? Our answer is that informative tokens come from two regions: positions with high student entropy, and positions with low student entropy plus high teacher--student divergence, where the student is overconfident and wrong.
Empirically, student entropy is a strong first-order proxy: retaining 50% of tokens with entropy-based sampling matches or exceeds all-token training while reducing peak memory by up to 47%. But entropy alone misses a second important region. When we isolate low-entropy, high-divergence tokens, training on fewer than 10% of all tokens nearly matches full-token baselines, showing that overconfident tokens carry dense corrective signal despite being nearly invisible to entropy-only rules.
We organize these findings with TIP (Token Importance in on-Policy distillation), a two-axis taxonomy over student entropy and teacher--student divergence, and give a theoretical explanation for why entropy is useful yet structurally incomplete. This view motivates type-aware token selection rules that combine uncertainty and disagreement. We validate this picture across three teacher--student pairs spanning Qwen3, Llama, and Qwen2.5 on MATH-500 and AIME 2024/2025, and on the DeepPlanning benchmark for long-horizon agentic planning, where Q3-only training on <20% of tokens surpasses full-token OPD. Our experiments are implemented by extending the OPD repository https://github.com/HJSang/OPSD_OnPolicyDistillation, which supports memory-efficient distillation of larger models under limited GPU budgets.