Related papers: Steered LLM Activations are Non-Surjective
Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time. However, current methods suffer from two key limitations:…
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…
Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…
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…
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…
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…
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…
Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…
Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We…
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison…
Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…
One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…
Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods primarily rely on prompt engineering, which often lacks stability and interpretability.…
Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant activation vectors with scalars? We argue that successfully…
We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…
Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…
Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at…
Activation probes are attractive monitors for AI systems due to low cost and latency, but their real-world robustness remains underexplored. We ask: What failure modes arise under realistic, black-box adversarial pressure, and how can we…
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…