conftrace_

safety realignment

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

safety alignment (2) parameter removal (1) harmful queries (1) neuron restoration (1) harmless helpful honest (1) neuron transplantation (1) alignment safety (1) task arithmetic (1) fine-tuned language model (1) fine-tuning attack (1)

Papers

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models ACL 2025 NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024