Tag
该论文提出一种训练无关的权重编辑方法，通过少量对比提示对直接修改模型权重，降低指令微调模型对有害指令（如说谎、性别歧视）的服从率，并在五个模型上验证了其优于激活引导等方法的鲁棒性。
Decoy Direction Optimization (DDO) is a fast, post-hoc defense method that protects open-weight LLMs from refusal feature ablation attacks by injecting decoy signals into the network, achieving high robustness at lower cost than trained defenses.
The paper introduces AMRA, a weight-editing method to mitigate abliteration in large language models by obscuring the refusal signal, improving post-abliteration refusal scores on Llama-3-8B and Gemma-2-9B with minimal utility degradation.