Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
arXiv:2609.02998v2 Announce Type: replace-cross Abstract: 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…
Read the full story at arXiv cs.AI ↗
ImpactNotable 31/100
Why it mattersRule-based estimate: event keywords (+4); trust 6/10.
RegionsGlobal
Published5 h ago (Fri, 18 Sep 2026 04:00:00 GMT)
RetrievedFri, 18 Sep 2026 08:00:48 GMT via rss
ClassifiedFri, 18 Sep 2026 08:01:04 GMT by heuristic
AuthorZhiwei Zhang, Zechen Sun, Fei Zhao, Kang Peng, Bin Liang, Huayu Deng, Yao Hu, Kam-Fai Wong, Mu Chuan