arXiv Statistics ML
Unbiased Top-$k$ Estimation for On-Policy Distillation
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv AI
Aug 18
Tail-Aware Top-$k$ On-Policy Distillation
arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv Machine Learning
Jul 7
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.
arXiv AI
Jun 24
On the Position Bias of On-Policy Distillation
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.
arXiv Machine Learning
Sep 1
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation
arXiv:2608.29846v1 Announce Type: cross Abstract: Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teach...
arXiv Machine Learning
Aug 27
A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
The paper investigates how the sampled-token reverse-KL loss in on‑policy distillation distributes updates across tokens. By analyzing the gradient of the per‑token K2 estimator, the authors find that tokens with low student probability and large teacher‑student gaps receive disproportionately large gradient norms. They propose Surprise‑aware Reweighting (SuRe), a lightweight weighting rule that further amplifies this allocation, and demonstrate that SuRe improves math metrics on Qwen3 student models without harming out‑of‑domain performance.
arXiv AI
3d ago
Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OP...