SOURCE-LINKED INTELLIGENCE

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision from a frozen teacher on the student's own rollouts. Vanilla OPD applies this supervision uniformly across prompts, without checking whether the teacher is reliable for each prompt. Because reverse KL is mode-seeking, a confidently wrong teacher can induce a strong yet misleading update. Distributional proxies, such as entropy or teacher-student likelihood agreement, measure uncertainty or agreement but do not directly verify outcome correctness. We introduce Teacher-Gated On-Policy Distillation (

Read original source ↗ Open in workspace

recordType

paper

region

Global