Related papers: Role-Conditioned Refusals: Evaluating Access Contr…
LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing scale imbalance. We propose treating verbal feedback as a…
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be…
As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning…
Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…
Over the years, access control systems have become increasingly more complex, often causing a disconnect between what is envisaged by the stakeholders in decision-making positions and the actual permissions granted as evidenced from access…
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on…
Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow administrators to write policies implementing access control rules which specify how access to private…
Large language models are meticulously aligned to be both helpful and harmless. However, recent research points to a potential overkill which means models may refuse to answer benign queries. In this paper, we investigate the factors for…
Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery method, Iterated Prefill Crawler (IPC), that uses token…
Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability, while existing metrics fail to capture this ability. In this…
Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for…
Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…
It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…
Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies or an indication of political censorship, that is practiced…
It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…
Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…
The rise of Large Language Models (LLMs) has revolutionized our comprehension of intelligence bringing us closer to Artificial Intelligence. Since their introduction, researchers have actively explored the applications of LLMs across…
Large Language Models (LLMs) can translate natural language into SQL, but small models struggle with multi-table and complex queries in Zero-Shot Learning (ZSL) settings. While Supervised Fine-Tuning (SFT) helps, it falls short for harder…
As large language models (LLMs) are increasingly deployed in high-stakes settings, their ability to refuse ethically sensitive prompts-such as those involving hate speech or illegal activities-has become central to content moderation and…
Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise…