发表机构
National University of Singapore; Hanoi University of Science and Technology（新加坡国立大学; 河内理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出核化激活引导（KAS）框架，将激活引导提升至再生核希尔伯特空间，实现局部自适应非线性引导，在越狱大语言模型和图像风格控制等任务中优于或媲美现有方法。
AI 中文摘要
激活引导为控制生成模型（如情感、风格和有用性）的属性提供了一种简单且无需训练的机制。然而，标准方法（如均值差分）在所有激活上应用单一的、与输入无关的引导向量，限制了表达能力，并忽略了激活空间的局部几何结构。我们提出了核化激活引导（KAS），这是一个统一框架，将激活引导提升到再生核希尔伯特空间。KAS将引导表述为一个纯粹通过核评估表达的优化问题，从而在不构造显式特征映射的情况下，产生一个隐式的、依赖于激活的引导分数。与DiM不同，KAS引入了局部自适应引导：每个激活根据其相对于源和目标参考集的位置进行修改，从而在表示空间上产生一个非线性的引导场。重要的是，在线性核下，DiM作为KAS的一个特例被恢复，而更丰富的核则能够实现几何感知的干预。在标准的激活引导任务中，包括越狱大语言模型和图像风格控制，KAS的表现优于或与现有方法相当。
英文摘要
Activation steering provides a simple, training-free mechanism for controlling attributes of generative models such as sentiment, style, and helpfulness. However, standard approaches such as Difference-in-Means apply a single input-independent steering vector across all activations, limiting expressivity and ignoring the local geometry of the activation space. We propose Kernelized Activation Steering (KAS), a unifying framework that lifts activation steering into a reproducing kernel Hilbert space. KAS formulates steering as an optimization problem expressed purely via kernel evaluations, yielding an implicit, activation-dependent steering score without constructing explicit feature maps. Unlike DiM, KAS induces locally adaptive steering: each activation is modified according to its relative position with respect to source and target reference sets, producing a nonlinear steering field over the representation space. Importantly, DiM is recovered as a special case under a linear kernel, while richer kernels enable geometry-aware interventions. Across standard activation steering tasks, including jailbreaking LLMs and image style control, KAS outperforms or is on par with the existing methods.
CommentsNeurIPS 2026
