Related papers: Steering in the Shadows: Causal Amplification for …

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…

Large vision-language models (LVLMs) have achieved remarkable performance on multimodal tasks. However, they still suffer from hallucinations, generating text inconsistent with visual input, posing significant risks in real-world…

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…

Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted prompts bypass safety mechanisms. Understanding the causal factors behind such…

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…

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

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…

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…

Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts. We investigate the internal basis of this behavior via mechanistic interpretability. Using open-sourced…

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of…

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

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 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…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…