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

Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. While fine-tuning enhances performance by internalizing domain…

The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model's output, hoping for a responsive model that can complete responses according to their…

Many languages and algebras have been proposed in recent years for the specification of authorization policies. For some proposals, such as XACML, the main motivation is to address real-world requirements, typically by providing a complex…

Current evaluation of large language models (LLMs) overwhelmingly prioritizes accuracy; however, in real-world and safety-critical applications, the ability to abstain when uncertain is equally vital for trustworthy deployment. We introduce…

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…

LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential disclosure, data exfiltration, and unauthorized output) that safety evaluations assume hold…

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Large Language Models (LLMs) have made significant progress in assisting users to query databases in natural language. While LLM-based techniques provide state-of-the-art results on many standard benchmarks, their performance significantly…

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Proper implementation of technical and administrative controls reinforces an organization's cybersecurity posture and business resilience, reduces risks, and enhances governance, ultimately elevating business maturity. The dynamics of the…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this…

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…

Large language models (LLMs) have revolutionized natural language interfaces for databases, particularly in text-to-SQL conversion. However, current approaches often generate unreliable outputs when faced with ambiguity or insufficient…

Significant research has been done in the area of Role Based Access Control [RBAC]. Within this research there has been a thread of work focusing on adding parameters to the role and permissions within RBAC. The primary benefit of parameter…

The analysis of hidden channels of information leakage with respect to role-based access control includes monitoring of excessive permissions among users. It is not always possible to completely eliminate redundancy. The problem of ranking…

Military Large Language Models (LLMs) must provide accurate information to the warfighter in time-critical and dangerous situations. However, today's LLMs are imbued with safety behaviors that cause the LLM to refuse many legitimate queries…

Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tokens should be transferred into the partially decoded…

Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when…