Search: “safety”

arXiv:2609.08080v1 Announce Type: new Abstract: Ensuring safety in reinforcement learning under nonstationarity requires anticipating changes in risk before they lead to unsafe behavior. Existing appr

arXiv:2609.04714v1 Announce Type: cross Abstract: Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models s

arXiv:2601.22118v3 Announce Type: replace Abstract: Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in

During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as 'reverse engineering' We were in contact with the Anthropic team the

arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialec

arXiv:2608.30889v1 Announce Type: cross Abstract: Deploying a new control policy for voltage control in active distribution grids requires evidence that physical limits will be satisfied before the po

arXiv:2608.24275v1 Announce Type: new Abstract: Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware saf

arXiv:2608.21735v1 Announce Type: new Abstract: This paper presents a safety-critical bilateral teleoperation framework for omnidirectional aerial manipulators that integrates visual and force-sensorl

arXiv:2608.16913v1 Announce Type: new Abstract: Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive i

arXiv:2608.13304v1 Announce Type: new Abstract: Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped b

arXiv:2608.03028v1 Announce Type: new Abstract: Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations

arXiv:2607.28196v1 Announce Type: new Abstract: Practitioners accept a compressed language model once it clears a stack of data-cheap quality guards: perplexity within a small factor of the original,

arXiv:2607.26820v1 Announce Type: new Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk

arXiv:2607.23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.

Sam Altman: “Concentration of power with AI is a terrifying thing.” 'A lot of the talk about safety concerns is well-founded, and then a lot of it is about people that just really, even if it's slight

arXiv:2607.19534v1 Announce Type: new Abstract: Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typ

arXiv:2512.01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety

arXiv:2503.15581v2 Announce Type: replace Abstract: Real-time safety assessment is critical for ensuring the reliable operation of complex dynamic systems. However, obtaining full safety labels in rea

arXiv:2607.05407v1 Announce Type: cross Abstract: Modern artificial intelligence (AI) systems present profound new risks to child safety. AI is increasingly being misused to create AI-generated child

arXiv:2607.00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent metho

arXiv:2606.30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while th

arXiv:2606.27210v1 Announce Type: new Abstract: We argue that safety classifiers should model user intent as an explicit signal between the prompt and the final label. To study this, we introduce AIMS

arXiv:2606.05523v1 Announce Type: new Abstract: Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can byp

arXiv:2606.04778v1 Announce Type: new Abstract: Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent

arXiv:2606.02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate t

arXiv:2510.09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches pr

arXiv:2605.31073v1 Announce Type: new Abstract: Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do

arXiv:2605.28030v1 Announce Type: cross Abstract: Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversa

arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe co

arXiv:2605.21834v1 Announce Type: new Abstract: Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Con

arXiv:2605.14174v1 Announce Type: new Abstract: Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet

arXiv:2605.09383v1 Announce Type: new Abstract: In safety-critical scenarios, the protection level of the autonomous navigation system is crucial for enabling mobile robots to perform safe tasks. Howe

arXiv:2510.20129v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses des

arXiv:2605.04572v1 Announce Type: cross Abstract: Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors l

arXiv:2605.00667v1 Announce Type: new Abstract: Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominen

arXiv:2604.27193v1 Announce Type: new Abstract: Automatic Emergency Braking (AEB) systems represent a safety-critical national interest, with the National Highway Traffic Safety Administration (NHTSA)

arXiv:2604.27358v1 Announce Type: new Abstract: As large language model (LLM) agents are deployed in high-stakes environments, the question of how safely to delegate subtasks to specialized sub-agents

arXiv:2602.16729v3 Announce Type: replace-cross Abstract: We systematically evaluate the quality of widely used adversarial safety datasets from two perspectives: in isolation and in practice. In isol

arXiv:2503.17239v3 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show

arXiv:2505.16737v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises s

arXiv:2604.19559v1 Announce Type: new Abstract: Construction workers are highly vulnerable to heat stress, yet tools that translate real-time physiological data into actionable safety intelligence rem

arXiv:2604.19639v1 Announce Type: cross Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner mu

arXiv:2604.17210v1 Announce Type: new Abstract: Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing sa

arXiv:2604.17391v1 Announce Type: cross Abstract: RISC-V is emerging as a viable platform for automotive-grade embedded computing, with recent ISO 26262 ASIL-D certifications demonstrating readiness f

arXiv:2603.14975v2 Announce Type: replace-cross Abstract: Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering

arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their sta