arXiv AI
Solving Without Stopping: On-Policy Distillation at Small Scale
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 28
Masked Distillation: Internalizing the Chain-of-Thought in Language Models
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
arXiv Computation and Language
Sep 18
What Does Privileged Information Add to On-Policy Self-Distillation?
The paper investigates how privileged information—such as a teacher’s full solution or reasoning trace—affects on‑policy self‑distillation (OPSD) in language models. Using the AMPLE‑Math benchmark, the authors compare distillation with and without extra teacher views, finding that reference‑free distillation explains most gains for Qwen3‑1.7B, while additional references provide modest benefits, especially for polished solutions. The study also shows that the impact of privileged data depends on the student’s training regime and that altering token‑level supervision can leave student behavior largely unchanged.
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
Jul 7
Rethinking On-Policy Self-Distillation for Thinking Models
arXiv:2607. 05184v1 Announce Type: new Abstract: Self-distillation is a promising recipe for self-improvement in language models.
arXiv AI
Jul 17
Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
arXiv:2607. 14552v1 Announce Type: cross Abstract: A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors.
arXiv Machine Learning
Jul 30
Weak-to-Strong On-Policy Distillation
arXiv:2607. 26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs.