When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment
Paper recorded by Signals 4 on 2026-09-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24
Category: cs.AI · 人工智能 · first seen 2026-09-24
Abstract
Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-generated responses, yet teacher preference need not reflect correctness. Recent hybrids combine OPD and verifier-derived advantages or reweight task credit using
Read on arXiv →
Cite this page: When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment: the #8 most recent of 380 cs.AI papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/when-and-where-to-trust-the-teacher-unifying-on-policy-distillation-and-grpo-thr.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free