Tail-Aware Top-$k$ On-Policy Distillation

[2608.14728] Tail-Aware Top-$k$ On-Policy Distillation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14728 (cs) [Submitted on 12 Aug 2026] Title: Tail-Aware Top-$k$ On-Policy Distillation Authors: Huipeng Huang , Hongxin Wei View a PDF of the paper titled Tail-Aware Top-$k$ On-Policy Distillation, by Huipeng Huang and 1 other authors View PDF HTML (experimental) Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories. To provide dense supervision at tractable cost, many works minimize the reverse Kullback-Leibler (KL) divergence between the student and teacher's normalized distributions over the teacher's top-$k$ tokens. However, this normalized objective discards the information about tail probability: the total probability outside the teacher's top-$k$ tokens. As a result, the optimization can steadily increase the student's tail probability and entropy, empirically degrading downstream accuracy. To address this issue, we propose Tail-Aware Top-$k$ OPD (\textbf{TA-OPD}), a novel distillation method that restores the missing tail probability signal. In particular, TA-OPD minimizes the reverse KL divergence over the top-$k$ tokens plus a tail token that carries the tail probability. In effect, TA-OPD better aligns the student's next-token distribution with the teacher's, preventing the increase in tail probability and entropy caused by top-$k$ normalization. Extensive experiments demonstrate the superiority of TA-OPD, improving Avg@8 by up to 8.05 points on common benchmarks. Our code is available at this https URL . Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2608.14728 [cs.LG] (or arXiv:2608.14728v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14728 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Huipeng Huang [ view email ] [v1] Wed, 12 Aug 2026 20:31:49 UTC (977 KB) Full-text links: Access Paper: View a PDF of the paper titled Tail-Aware Top-$k$ On-Policy Distillation, by Huipeng Huang and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Weak-to-Strong Generalization via Direct On-Policy Distillation#343457
• Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation#668050
• Blockwise Policy-Drift Gating for On-Policy Distillation#303233
• PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty#1119372
• On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity#307000