hiw3c 日报精选
arXiv cs.AI/CL/LG 网页快照

在学生所处状态处与其对接:以学生为前缀的教师适配用于在策略上蒸馏

原文标题 · Meet Students Where They Are: Student-Prefix Teacher Adaptation for On-Policy Distillation

作者: Xue Zhang, Songming Zhang, Yunlong Liang | 在策略上蒸馏(OPD)通过基于学生生成的轨迹进行优化,缓解了学生的暴露偏差问题。然而,学生生成的前缀可能包含推理错误,或遵循教师不熟悉的模式,从而削弱其词元级监督的可靠性。随着前缀变长,这种性能下降愈发明显。为解决这一教师侧分布失配

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Computer Science > Computation and Language

Title: Meet Students Where They Are: Student-Prefix Teacher Adaptation for On-Policy Distillation

Abstract: On-policy distillation (OPD) mitigates the student's exposure bias by optimizing on student-generated trajectories. However, student-generated prefixes may contain reasoning errors or follow patterns unfamiliar to the teacher, undermining the reliability of its token-level supervision. This degradation becomes more pronounced as prefixes grow longer. To address this teacher-side distribution mismatch, we propose Student-Prefix Teacher Adaptation (SPTA), which adapts the teacher to the states on which it is queried during distillation. Specifically, before OPD starts, we collect student rollout prefixes with random lengths and continually train the teacher to continue from the prefixes using reinforcement learning with verifiable rewards (RLVR). By treating each prefix as context and rewarding correct final answers, the teacher learns to recover from student-induced states rather than imitate the student's reasoning. Then, the adapted teacher is used for standard OPD, with no changes to the distillation objective. Experiments on mathematical reasoning benchmarks show that our SPTA improves average student performance over standard OPD and OPD with task-level RLVR-adapted teachers. These results highlight the importance of adapting teachers not only to solve problems independently, but also to provide reliable guidance on the states their students actually visit.

Submission history

Access Paper:

Additional Features

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .