Related papers: Programming Refusal with Conditional Activation St…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…
Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…
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…
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…
Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…
The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes in model activations,…
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…
This paper investigates privacy jailbreaking in LLMs via steering, focusing on whether manipulating activations can bypass LLM alignment and alter response behaviors to privacy related queries (e.g., a certain public figure's sexual…
We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in residual stream…
We address the challenge of societal bias in Large Language Models (LLMs), focusing on the Llama 2 7B Chat model. As LLMs are increasingly integrated into decision-making processes with substantial societal impact, it becomes imperative to…
An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…
Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…
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…
Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…
As large language models (LLMs) evolve in complexity and capability, the efficacy of less widely deployed alignment techniques are uncertain. Building on previous work on activation steering and contrastive activation addition (CAA), this…
Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at…
Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, frequently failing at simple robotic tasks. To mitigate this,…
Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it and generate false statements. This gap between "knowing" and "telling" poses a…
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…