Signals 4 · free daily AI digest

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

Paper recorded by Signals 4 on 2026-10-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-14 on arXiv · recorded by Signals 4 on 2026-10-15

Category: cs.AI · 人工智能 · first seen 2026-10-15

Abstract

On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teacher and show it fails on incorrect rollouts: the teacher follows student errors, although it recognizes them. We propose CriticOPD, using erro

Read on arXiv →

#310 most recent of 960 cs.AI papers we have recorded · ↑ newer: Beyond LLM Judge: Mechanical Verification for Agentic Autoformalizatio · ↓ older: Scaling Discovery Requires Forgetting

Cite this page: Recovering Reliable Supervision via Critique-Guided On-Policy Distillation: the #310 most recent of 960 cs.AI papers we have recorded (as of 2026-10-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/recovering-reliable-supervision-via-critique-guided-on-policy-distillation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json

Related: More cs.AI papers · arXiv signals · All papers · Today in AI

Get 4 AI signals a day by email — free.

Subscribe free → See all plans →

Get 4 AI signals a day by email — free

All models · All repos · By company · Daily editions