arXiv AI
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Aug 26
One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of...
arXiv Machine Learning
Aug 27
One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
The paper reviews On‑Policy Self‑Distillation (OPSD), a method where a language model learns from its own generations using privileged information such as reference solutions or plans, eliminating the need for a larger teacher model. It identifies a key failure mode—collapse, where the model’s reasoning paths narrow progressively—and analyzes it through three levers: signal application, privileged information, and teacher dynamics. The review focuses on mathematical reasoning, offering a unified vocabulary and distinguishing settled facts from ongoing debates.
arXiv AI
Sep 30
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...
Hugging Face Trending Papers
Jul 6
Weak-to-Strong Generalization via Direct On-Policy Distillation
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.
arXiv AI
Oct 1
On the Off-Policy Teacher in On-Policy Distillation
The paper introduces SCOUT, a co‑training framework that adapts an off‑policy teacher to better continue from student‑generated prefixes in on‑policy distillation (OPD). By periodically optimizing the teacher’s conditional continuation ability using reinforcement learning with verifiable rewards, SCOUT improves the teacher’s performance on student prefixes. Experiments across various teacher‑student setups, model scales, and reasoning domains show that SCOUT consistently enhances the effectiveness of OPD.
arXiv AI
Aug 6
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.