Bewaard in:
Bibliografische gegevens
Hoofdauteurs: Liu, Yanjiang, Lou, Jie, Guan, Xinyan, Ji, Yuqiu, Lin, Hongyu, He, Ben, Han, Xianpei, Sun, Le, Yu, Xing, Lu, Yaojie
Formaat: Preprint
Gepubliceerd in: 2026
Onderwerpen:
Online toegang:https://arxiv.org/abs/2605.30833
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!
Inhoudsopgave:
  • On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identify a critical bottleneck, \textbf{Supervision Fidelity Decay (SFD)}: as student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative. Consequently, the teacher-dependent corrective signal in reverse-KL distillation weakens, causing student drift to compound across long reasoning chains. To mitigate SFD, we introduce \textbf{Lookahead Group Reward (\ours{})}. Building on the insight that next-step teacher confidence reflects the discriminative strength of future reverse-KL supervision, \ours{} evaluates the student's top-K candidate tokens by the teacher confidence they induce at the subsequent step and assigns a group-normalized reward. To maintain computational efficiency, we further design an entropy-triggered tree-attention mechanism. Across six math and code benchmarks, \ours{} improves mean@8 by \textbf{2.57} points over OPD for a 7B student, with gains increasing in longer-generation and reaching +\textbf{4.92} points on AIME-26 at 39k tokens.