On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to teacher logits, enabling OPD using only teacher-generated responses. To prove it, we introduce ROPD, a simple yet foundational framework for rubric-based OPD. Specifically, ROPD induces prompt-specific rubrics from teacher-student contrasts, and then utilizes these rubrics to score the student rollouts for on-policy optimization. Empirically, ROPD outperforms the advanced logit-based OPD methods across most scenarios, and achieving up to a 10x gain in sample efficiency. These results position rubric-based OPD as a flexible, black-box-compatible alternative to the prevailing logit-based OPD, offering a simple yet strong baseline for scalable distillation across proprietary and open-source LLMs. Code is available at https://github.com/Peregrine123/ROPD_official.
@article{arxiv.2605.07396,
title = {Rubric-based On-policy Distillation},
author = {Junfeng Fang and Zhepei Hong and Mao Zheng and Mingyang Song and Gengsheng Li and Houcheng Jiang and Dan Zhang and Haiyun Guo and Xiang Wang and Tat-Seng Chua},
journal= {arXiv preprint arXiv:2605.07396},
year = {2026}
}
Comments
Preprint. Code is available at https://github.com/Peregrine123/ROPD_official