Related papers: SafeCtrl-RL: Inference-Time Adaptive Behaviour Con…

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…

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in security reasoning and brittleness to evolving vulnerability patterns raise critical…

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel…

Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks. Existing safety techniques -- including external…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to…

User prompts to large language models (LLMs) are often ambiguous or under-specified, and subtle contextual cues shaped by user intentions, prior knowledge, and risk factors strongly influence what constitutes an appropriate response.…

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on…