Related papers: Role-Conditioned Refusals: Evaluating Access Contr…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavior of LLMs under sustained authority pressure is still an…

The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We…

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…

Reinforcement learning (RL) has demonstrated significant promise in enhancing the reasoning capabilities of Text2SQL LLMs, especially with advanced algorithms such as GRPO and DAPO. However, the performance of these methods is highly…

Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for…

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…

Process roles are used to structure complex engineering processes in single sys-tems development for many years. Typically, each role has specific responsi-bilities from which certain information demands originate. In the engineering of…

This paper presents an empirical investigation into the capabilities of Large Language Models (LLMs) to perform automated Attribute-based Access Control (ABAC) policy mining. While ABAC provides fine-grained, context-aware access…

Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…

In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of semi-realistic role-playing exercises designed to elicit…

Least privilege is a core security principle: grant each request only the minimum access needed to achieve its goal. Deployed language models almost never follow it, instead being exposed through a single API endpoint that serves all users…

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…

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as "I don't know", RAIT enhances…

The rapid growth of large language models has spurred significant interest in model compression as a means to enhance their accessibility and practicality. While extensive research has explored model compression through the lens of safety,…

This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…

Recent advances in large language models (LLMs) have significantly improved performance on the Text-to-SQL task by leveraging their powerful reasoning capabilities. To enhance accuracy during the reasoning process, external Process Reward…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. In particular, little is known about how users respond when models refuse to answer a prompt-one of the…

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…