这篇论文提出了一种叫接种适配器的新方法，用LoRA在训练时强化不想有的特征，比之前的接种提示更好用，后门更少，适合关心AI安全的人看。
该论文提出接种适配器（Inoculation Adapters, IA），基于LoRA在训练时强化不良特征以减轻优化压力。方法分三步：在不良特征上训练IA，冻结IA同时训练任务适配器，部署时丢弃IA仅保留任务适配器。在6个模型家族和包括突发性错位（emergent misalignment）在内的多种不良特征上，IA比接种提示（inoculation prompting）更有效抑制不良特征。同时避免接种提示的两个缺点：无法可靠通过提示诱发的特征抑制、引入较少意外后门。但IA在保留期望特征方面未一致优于接种提示，仍是挑战。
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
Inoculation prompting is a selective generalization technique used against Emergent Misalignment. We introduce inoculation adapters (IA), which similarly diminish the optimization pressure to learn undesired traits by strengthening the trait at train time. Inoculation adapters are LoRAs that are trained and used over three steps: 1) trained on undesired traits; 2) attached frozen while a separate task adapter is trained on data exhibiting both desired and undesired traits; 3) at deployment, the IA is discarded, and only the task adapter is kept. We show across six model families and several undesired traits including emergent misalignment, that inoculation adapters are more effective at suppressing undesired traits, while avoiding two drawbacks of inoculation prompting: inoculation adapters can suppress capabilities and traits that cannot be reliably elicited by a prompt, and they introduce fewer surprising backdoors than inoculation prompting under our probes. While undesired traits are better suppressed by inoculation adapters, the retention of desired traits is not consistently improved upon inoculation prompting and remains a challenge for both techniques.