Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation 事件

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation arXiv:2606.08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a steering vector from examples of a target behavior and injecting it into intermediate activations during inference, activation steering enables flexible behavioral control while avoiding the permanent parameter update