cs.LGNov 1, 2026

OC-OPD: Observation-coordinated Supervision for On-Policy Distillation

Authors: Ruoran Xu, Yilun Zhao, Ziyu Chen, Arman Cohan

Organizations: Yale NLP Lab

Abstract

Reverse and forward Kullback--Leibler (KL) divergences provide complementary supervision in on-policy distillation: reverse KL refines the student's active token rankings, and forward KL allocates mass to teacher-supported candidates. At student-generated prefixes, we form a four-observation matrix by treating the student and teacher as both candidate sources and evaluators. The diagonal self-observations measure uncertainty, while source-centered cross-observations recover the two KL objectives. We establish an exact identity equating the Fisher inverse-metric coupling of their logit gradients with the sum of these contrasts, yielding a common local descent direction for distinct positive distributions. Observation-coordinated on-policy distillation (OC-OPD) uses observations to set preferences, closed-form bargaining to coordinate gradients, and distributional discrepancy to scale the update. Across three heterogeneous student settings (non-thinking generation, thinking generation, and base-model initialization), OC-OPD achieves strong gains in mathematical reasoning and transfers effectively to out-of-distribution scientific question answering and code generation. Our code is publicly available at: https://github.com/RuoranXu/OC-OPD.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 5, 2026

Reinforcing What the Student Has Learned: Teacher-Guided On-Policy Distillation

On-policy distillation (OPD) improves language-model reasoning through dense teacher feedback on student-generated responses. We first observe an amplitude disparity in this feedback: on math reasoning responses, style-related positions exhibit 3.5 times the mean absolute teacher--student log-probability difference of mathematical positions. Scaling OPD updates by these discrepancies thus directs much of the update strength toward matching the teacher's expression. We instead take the student's own pretrained base as a reference: the student--base difference records the token preferences acquired during post-training and provides supervision that does not depend on the student's distance from the teacher. Building on this reference, we propose Student-Delta On-Policy Distillation (SD-OPD), which uses centered student--base differences as update coefficients, keeps each coefficient only when its sign agrees with centered teacher--student feedback, and recomputes the student signal every training round. Across 5 teacher--student configurations with Qwen3 students of 1.7B to 8B parameters, SD-OPD improves six-task mathematics average pass@1 (avg@16) over OPD by 7.76 to 10.37 percentage points. Code is available at https://github.com/aim-uofa/sd-opd.
Aug 26, 2026

A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation

On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood. We analyze the gradient of the per-token K2 estimator of reverse KL with respect to the student logits. The ℓ1\ell_1 norm of this gradient factorizes into the absolute teacher--student log-probability gap and a student-side softmax factor that grows as the sampled token becomes less likely under the student. In our math-distillation runs, these per-token norms are highly non-uniform: low-student-probability tokens account for a disproportionate share of their sum and are also enriched in large teacher--student gaps. As a lightweight intervention suggested by this analysis, we study Surprise-aware Reweighting (SuRe), a detached, bounded weighting rule that further amplifies this existing allocation. Across two Qwen3 student scales, SuRe improves several math metrics over vanilla OPD and shows no clear degradation on the selected out-of-domain benchmarks. Our primary contribution is therefore a gradient-level characterization of reverse-KL OPD trained with the K2 estimator, with SuRe as one empirical instantiation.
Sep 18, 2026

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does not purely reflect the capability gap between the teacher and the student: it also contains deviations arising from the teacher itself, which are consequently mixed into the observed teacher--student discrepancy and indiscriminately learned by standard OPD during training. This issue is further exacerbated by privileged OPD, where privileged information induces larger teacher-side likelihood shifts, thereby encouraging the student to learn more of the teacher's own deviation. We introduce Calibrated On-Policy Distillation (Cal-OPD), which estimates the teacher's self-deviation region through positive and negative privileged interventions and calibrates the original teacher--student discrepancy by retaining only the component that lies beyond this region. Experiments on mathematical reasoning benchmarks show that, while retaining only about 52--65% of the original teacher--student discrepancy as the optimization signal, Cal-OPD consistently outperforms standard OPD and its variants across model scales.