Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 10339v1 Announce Type: cross Abstract: Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to estimate and rank the causal effects of such interventions.
arXiv:2608. 10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether medication-safety boundaries persist across follow-ups after explicit self-treatment intent.
arXiv:2602. 24287v2 Announce Type: replace-cross Abstract: In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses.
arXiv:2608. 10289v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios.
arXiv:2608. 10056v1 Announce Type: cross Abstract: Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians and obstacles.
arXiv:2608. 10273v1 Announce Type: cross Abstract: Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting patient data to closed-source commercial LLMs and the lack of systematic evaluation of fine-tuning strategies for locally deployable open-source small language models (SLMs).
arXiv:2608. 10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints.
arXiv:2608. 10047v1 Announce Type: cross Abstract: In modern industry, keeping complex systems reliable, safe, and efficient hinges on Prognostics and Health Management (PHM).
arXiv:2608. 10126v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity.
arXiv:2608. 10562v1 Announce Type: new Abstract: Not all clicks are equal.
arXiv:2608. 09972v1 Announce Type: cross Abstract: First-generation AI weather models are often reported to underperform at extremes, mostly in reanalysis-based evaluations of deterministic regression systems.
arXiv:2608. 10256v1 Announce Type: new Abstract: Accurate vessel trajectory prediction is critical for maritime safety and anomaly detection, yet existing models often struggle with geographic bias and navigational realism.
arXiv:2608. 10149v1 Announce Type: new Abstract: Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples.
arXiv:2608. 10709v1 Announce Type: new Abstract: Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation.
arXiv:2608. 10344v1 Announce Type: cross Abstract: Thermo-mechanical compliant devices are commonly designed with small-strain linear elasticity and temperature-independent material properties, even though they might operate hundreds of kelvin above ambient where both assumptions are questionable.
arXiv:2608. 10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored.
arXiv:2608. 11006v1 Announce Type: cross Abstract: Governments worldwide have responded to the rapid expansion of AI by publishing national and regional AI strategies.
arXiv:2605. 23146v3 Announce Type: replace-cross Abstract: Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy.
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
arXiv:2608. 09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure behind visual layout.