conftrace_

alignment safety

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neuron transplantation (1) safety realignment (1) large language model (1) domain expertise (1) fine-tuning attack (1) parameter-efficient tuning (1) synthetic data (1) parameter efficient (1) safety alignment (1) synthetic data generation (1)

Papers

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024