arXiv:2606.03089v3 Announce Type: replace-cross
Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision. Prior work has shown that OPSD can collapse in verifiable reasoning tasks, while safety alignment differs in that it is guided by high-level constitutions rather than explicit target answers. However, pilot studies reveals that safety OPSD nonetheless suffers from severe collapse, where constitutional conditioning contracts the teacher distribution toward short and overly conservative responses and Reverse KL further amplifies this contraction into reduced expressiveness. We formalize this effect as geometric leakage under safety boundaries in a non-orthogonal semantic space, where safety pressure transfers into the expressiveness dimension. Based on this analysis, we propose Constitutional On-Policy Safety Distillation (COPSD), which first calibrates the teacher through a Cross-SFT cold-start and then performs constitution-conditioned on-policy distillation. Experiments across 3 multimodal large language models (MLLMs) on 12 safety and general benchmarks show that COPSD improves both safety and helpfulness over baselines while reducing the safety tax on general reasoning.
Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision. Prior work has shown that OPSD can collapse in verifiable reasoning tasks, while safety alignment differs in that it is guided by high-level constitutions rather than explicit target answers. However, pilot studies reveals that safety OPSD nonetheless suffers from severe collapse, where constitutional conditioning contracts the teacher distribution toward short and overly conservative responses and Reverse KL further amplifies this contraction into reduced expressiveness. We formalize this effect as geometric leakage under safety boundaries in a non-orthogonal semantic space, where safety pressure transfers into the expressiveness dimension. Based on this analysis, we propose Constitutional On-Policy Safety Distillation (COPSD), which first calibrates the teacher through a Cross-SFT cold-start and then performs constitution-conditioned on-policy distillation. Experiments across 3 multimodal large language models (MLLMs) on 12 safety and general benchmarks show that COPSD improves both safety and helpfulness over baselines while reducing the safety tax on general reasoning.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article: