arXiv AI
KL for a KL: On-Policy Distillation with Control Variate Baseline
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Statistics ML
Oct 2
Unbiased Top-$k$ Estimation for On-Policy Distillation
The paper introduces Tail‑Corrected Top‑k On‑Policy Distillation (TT‑OPD), a method that improves on existing Top‑k OPD by combining the selected top‑k tokens with a sampled token from the student’s rollout. This hybrid approach recovers the probability mass discarded by limiting to top‑k, yielding an unbiased estimator of the reverse KL divergence gradient while maintaining low computational cost. Experiments show TT‑OPD outperforms other OPD variants in accuracy.
arXiv AI
Jun 17
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
arXiv:2606. 17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation.
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 Machine Learning
Jun 19
A Survey of On-Policy Distillation for Large Language Models
arXiv:2604. 00626v4 Announce Type: replace Abstract: As Large Language Models continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become an important engineering problem, and knowledge distillation remains a common technique for this transfer.
arXiv Machine Learning
Sep 30
REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse
arXiv:2609.37500v1 Announce Type: new Abstract: On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its relianc...
arXiv AI
Jun 19
Reinforcement-aware Knowledge Distillation for LLM Reasoning
arXiv:2602. 22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students.