Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Yanjiang, Lou, Jie, Guan, Xinyan, Ji, Yuqiu, Lin, Hongyu, He, Ben, Han, Xianpei, Sun, Le, Yu, Xing, Lu, Yaojie
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917547218042880
author Liu, Yanjiang
Lou, Jie
Guan, Xinyan
Ji, Yuqiu
Lin, Hongyu
He, Ben
Han, Xianpei
Sun, Le
Yu, Xing
Lu, Yaojie
author_facet Liu, Yanjiang
Lou, Jie
Guan, Xinyan
Ji, Yuqiu
Lin, Hongyu
He, Ben
Han, Xianpei
Sun, Le
Yu, Xing
Lu, Yaojie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30833
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
Liu, Yanjiang
Lou, Jie
Guan, Xinyan
Ji, Yuqiu
Lin, Hongyu
He, Ben
Han, Xianpei
Sun, Le
Yu, Xing
Lu, Yaojie
Computation and Language
Artificial Intelligence
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.
title Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.30833