arXiv Machine Learning October 3, 2026 By Laziz U. Abdullaev, Minh-Hieu Pham, Bach Do, Khoat Than, Tan M. Nguyen

Kernelized Activation Steering

Read the original on arXiv Machine Learning →

Kernelized Activation Steering (KAS) introduces a training‑free method for controlling attributes of generative models by lifting activation steering into a reproducing kernel Hilbert space. It formulates steering as an optimization problem using only kernel evaluations, producing an implicit, activation‑dependent steering score that adapts locally to the geometry of the activation space. Unlike standard Difference‑in‑Means, KAS generates a nonlinear steering field and recovers DiM as a special case with a linear kernel, achieving comparable or superior performance on tasks such as jailbreaking LLMs and image style control.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv Machine Learning

Jul 31

Dynamically Scaled Activation Steering

arXiv:2512. 03661v2 Announce Type: replace Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation.

By Alex Ferrando, Xavier Suau, Jordi Gonz\`alez, Pau Rodriguez

diffusion safety

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

arXiv Machine Learning

Sep 10

Disentangling Steering Vectors

arXiv:2609.07037v1 Announce Type: new Abstract: Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional...

By Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi, Hisashi Kashima

llms

arXiv Machine Learning

Jun 16

High-Dimensional Random Projection for Activation Steering in Language Models

arXiv:2606. 15092v1 Announce Type: new Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs).

By Minh-Hieu Pham, Bach Do, Laziz Abdullaev, Tan Minh Nguyen, Khoat Than

llms benchmarks

arXiv Machine Learning

Sep 11

GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models

GeoSteer introduces a geometry-aware, optimization-based approach to norm-preserving activation steering in large language models. By formulating steering as a Riemannian optimization problem, it updates activations through a sequence of small geodesic steps guided by a learned nonlinear objective, avoiding fixed steering directions. Experiments on TruthfulQA, RealToxicityPrompts, and UltraFeedback show that GeoSteer consistently outperforms existing activation steering baselines, offering smoother, more stable, and more consistent steering behavior.

By Xuan Cuong Ngo, Hao Vo, Ngan Le

llms benchmarks

arXiv Computation and Language

Sep 22

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...

By Jiaqian Li, Yanshu Li, Kuan-Hao Huang

llms fine-tuning

One email a morning, machine-written

Related stories

Dynamically Scaled Activation Steering

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Disentangling Steering Vectors

High-Dimensional Random Projection for Activation Steering in Language Models

GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models