Related papers: Deactivating Refusal Triggers: Understanding and M…
Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…
Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…
Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…
Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…
Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…
Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…
Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…
Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…
Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…
Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…
This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…
This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…
While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…
Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this…
Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…
Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. We introduce…