Related papers: Mitigating the Safety-utility Trade-off in LLM Ali…

Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method -- that is contrastive learning, is generally based on instance discrimination tasks, i.e., individual…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models? We introduce a scalable framework that allows for in-context…

Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinforcement learning methods often assume fixed constraints or stable environmental…

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…

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…

The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources,…

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offline safe RL problem…

In safe Reinforcement Learning (RL), safety cost is typically defined as a function dependent on the immediate state and actions. In practice, safety constraints can often be non-Markovian due to the insufficient fidelity of state…

Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global…

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…

Safety has been recognized as the central obstacle to preventing the use of reinforcement learning (RL) for real-world applications. Different methods have been developed to deal with safety concerns in RL. However, learning reliable…

Safe reinforcement learning (RL) seeks to mitigate unsafe behaviors that arise from exploration during training by reducing constraint violations while maintaining task performance. Existing approaches typically rely on a single policy to…

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT introduces new safety challenges that extend beyond…