相关论文: Minimizing Collateral Damage in Activation Steerin…

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…

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…

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Recent advances in automated theorem proving use Large Language Models (LLMs) to translate informal mathematical statements into formal proofs. However, informal cues are often ambiguous or lack strict logical structure, making it hard for…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

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…

Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can distribute backdoored checkpoints that behave normally under…

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research focuses on interactions between a single LM and a single…

Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings…

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:…

Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimensions possesses magnitudes significantly larger than the rest.…

The rise of large language models (LLMs) has prompted increasing interest in their use as in-context learning agents. At the core of agentic behavior is the capacity for exploration, or the ability to actively gather information about the…

Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…

Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…

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…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…