MSD enables cross-lingual safety transfer in LLMs via self-distillation with Dual-Perspective Safety Weighting, improving safety in low-resource languages without target response data.
arXiv preprint arXiv:2603.07445 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Empirical comparison of alignment ablation methods on a 60-prompt security evaluation suite shows task-only LoRA achieves 0.87 mean security score with 0.13 unsafe compliance.
citing papers explorer
-
Multilingual Safety Alignment via Self-Distillation
MSD enables cross-lingual safety transfer in LLMs via self-distillation with Dual-Perspective Safety Weighting, improving safety in low-resource languages without target response data.
-
Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
Empirical comparison of alignment ablation methods on a 60-prompt security evaluation suite shows task-only LoRA achieves 0.87 mean security score with 0.13 unsafe compliance.