Search: “safety”

arXiv:2608.13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), whic

arXiv:2608.11498v1 Announce Type: new Abstract: Natural-language-based scenario generation offers an intuitive means of describing rare and complex driving interactions, yet it is still uncertain whet

arXiv:2509.13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets. While

arXiv:2608.09542v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent

arXiv:2608.08077v1 Announce Type: new Abstract: Theory of Space framework (ToS) assesses the spatial understanding of curiosity-driven Vision-Language Models (VLMs) under partial observability. As AI

arXiv:2608.08542v1 Announce Type: new Abstract: Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, c

arXiv:2608.05560v1 Announce Type: cross Abstract: Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, l

arXiv:2508.16440v2 Announce Type: replace-cross Abstract: Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments. Howeve

arXiv:2608.05086v1 Announce Type: new Abstract: Language models differ in how safely they behave and these differences are measured by safety benchmarks. But aggregated benchmark scores are hard to tr

arXiv:2608.02941v1 Announce Type: new Abstract: We audit five frontier large language models on native Bangla derogatory speech (gali) across six protocols to test a single hypothesis: Comprehension-C

arXiv:2608.00975v1 Announce Type: new Abstract: Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) app

arXiv:2607.26170v1 Announce Type: new Abstract: This study developed a hybrid computer vision method to quantify exposed skin from images for dermal exposure assessment. Using 170 indoor-painting imag

arXiv:2607.25468v1 Announce Type: new Abstract: In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer wh

arXiv:2607.22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem. SAGE is a safety-first, authoriz

arXiv:2607.20352v1 Announce Type: new Abstract: Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybri

arXiv:2607.19356v1 Announce Type: new Abstract: Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility a

arXiv:2607.13453v1 Announce Type: cross Abstract: Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use o

arXiv:2607.07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single 'pipe

arXiv:2607.06630v1 Announce Type: new Abstract: Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.25, EEGNet classi

arXiv:2607.03561v1 Announce Type: new Abstract: As AI models continue to develop powerful capabilities, it becomes critical that we are able to verify that their output is aligned with our intentions.

arXiv:2607.01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural

arXiv:2607.02079v1 Announce Type: new Abstract: We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art perfor

arXiv:2607.02376v1 Announce Type: new Abstract: Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large language models, world models, optimization eng

arXiv:2607.01153v1 Announce Type: cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an in

arXiv:2607.00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genu

arXiv:2607.00464v1 Announce Type: cross Abstract: Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern:

arXiv:2501.14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety ben

arXiv:2606.28725v1 Announce Type: new Abstract: Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, an

arXiv:2606.29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior th

arXiv:2606.26968v1 Announce Type: new Abstract: Speech-capable models are increasingly deployed in real-world applications across languages. Yet their safety and fairness beyond English settings and u

arXiv:2606.26529v1 Announce Type: cross Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We

arXiv:2606.26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places co

arXiv:2606.20686v1 Announce Type: new Abstract: Shared-space transportation operation requires low-speed autonomous platforms to navigate safely and efficiently among pedestrians, service robots, micr

arXiv:2606.09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call brain-pro

arXiv:2606.08172v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited con

arXiv:2606.08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these eva

arXiv:2606.06370v1 Announce Type: new Abstract: Wearable exoskeletons can augment human phys ical capabilities during complex activities. However, ensuring adaptation across diverse tasks while guaran

arXiv:2606.00975v1 Announce Type: new Abstract: LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delu

arXiv:2606.00747v1 Announce Type: cross Abstract: For low-altitude Unmanned Aerial Vehicle (UAV) autonomy, 3D spatial understanding is not merely a perception objective, but the safety interface betwe

arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both f

arXiv:2605.31146v1 Announce Type: cross Abstract: This paper investigates how User Experience Research (UXR) methods can be combined with AI-supported analysis to develop clearer design direction for

arXiv:2605.25893v1 Announce Type: new Abstract: Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring

arXiv:2605.24817v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become an increasingly important paradigm for scaling Large Language Models (LLMs). As MoE models are incr

arXiv:2605.25510v1 Announce Type: new Abstract: Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require

arXiv:2605.22984v1 Announce Type: cross Abstract: Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such a

arXiv:2602.07340v2 Announce Type: replace Abstract: Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment method