Related papers: Steering Awareness: Detecting Activation Steering …

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path toward actionable…

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…

Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how…

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model parameters frozen. However, large-scale evaluations such as…

Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unforeseen behaviours may occur at any time. While observing the…

Activation steering presupposes that task-relevant behaviors correspond to linear directions in activation space -- directions that should both steer the model and be readable along the unembedding. Function vectors (FVs), extracted as mean…

Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs,…

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer…

Steering vectors (SVs) have been proposed as an effective approach to adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and…

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal…

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are scarce. Activation Steering (AS) has emerged as a data-efficient method for generating…

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system…