COPSD uses a Cross-SFT cold-start followed by constitution-conditioned distillation to achieve stronger safety-helpfulness balance and lower safety tax on reasoning than prior on-policy self-distillation methods.
Cross-modality safety alignment
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.
citing papers explorer
-
Constitutional On-Policy Safe Distillation
COPSD uses a Cross-SFT cold-start followed by constitution-conditioned distillation to achieve stronger safety-helpfulness balance and lower safety tax on reasoning than prior on-policy self-distillation methods.
-
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.