Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
This work addresses the challenge of suppressing undesirable behaviors—such as sudden alignment failures—learned during model training while preserving desired capabilities and avoiding unintended backdoors. The authors propose the Inoculation Adapter (IA) method, which first trains a LoRA adapter specialized in capturing undesirable behaviors, then freezes this adapter to guide the training of the main task adapter. Only the main adapter is deployed, thereby reducing the optimization pressure that leads the model to acquire undesirable capabilities. Unlike prompt-based inoculation, IA effectively mitigates behaviors that are difficult to elicit via prompting and substantially diminishes the risk of accidental backdoors. Experiments across six model families demonstrate that IA achieves more selective capability suppression while enhancing both safety and general applicability.