相关论文: Extending Activation Steering to Broad Skills and …

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic…

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment. Current steering methods, such as vector addition and…

Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in…

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of…

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores…

Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as…