洪 喆沛

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 introduce ROPD, a rubric-based OPD framework that induces prompt-specific rubrics from teacher-student contrasts and uses them to score student rollouts for on-policy optimization. Empirically, ROPD outperforms advanced logit-based OPD methods across most scenarios and achieves up to a 10x gain in sample efficiency, positioning rubric-based OPD as a flexible, black-box-compatible alternative for scalable distillation across proprietary and open-source LLMs.