Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 05139v1 Announce Type: cross Abstract: Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result to plan a schedule.
arXiv:2607. 23191v2 Announce Type: replace Abstract: Fine-tuned code LLMs are often conditioned on a design-intent header to steer parametric CAD generation, but whether the model reads that header's content has been tested neither under execution-level scoring nor with a causal control.
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
arXiv:2601. 03808v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches.
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.
arXiv:2608. 02070v2 Announce Type: replace-cross Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios.
arXiv:2608. 04289v1 Announce Type: new Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects.
arXiv:2608. 04697v1 Announce Type: new Abstract: Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level.
arXiv:2608. 04018v1 Announce Type: cross Abstract: AI agents are increasingly embedded in organizational workflows, where they interact with external information sources and invoke digital tools to perform operational tasks.
arXiv:2608. 04366v1 Announce Type: cross Abstract: While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks.
arXiv:2608. 04398v1 Announce Type: cross Abstract: Robotic planning often involves multiple objectives with complex priority relationships, such as safety, efficiency, and regulatory compliance.
arXiv:2608. 04327v1 Announce Type: new Abstract: Explicit onshore tsunami inundation forecasting can improve public risk awareness, but deterministically predicted inundation boundaries under highly uncertain conditions, such as near-field tsunamis generated by megathrust earthquakes, may falsely imply safety outside the boundaries.
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
arXiv:2608. 04474v1 Announce Type: new Abstract: Data-driven decision pipelines combining predictive machine learning models with downstream optimization software are increasingly used to make high-stakes operational decisions.
arXiv:2608. 04686v1 Announce Type: new Abstract: We study distributionally robust PAC learning for the $0$--$1$-loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order $k>1$ and radius $\rho\geq 0$.
arXiv:2608. 04805v1 Announce Type: new Abstract: Leak detection models for multiphase pipelines often degrade when deployed under flow regimes that differ from training.
arXiv:2608. 04879v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized.
arXiv:2608. 04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate.
arXiv:2608. 04921v1 Announce Type: cross Abstract: As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments.
arXiv:2604. 26233v3 Announce Type: replace Abstract: As Large Language Models (LLMs) are proposed as legal decision assistants, and even first-instance decision-makers, across a range of judicial and administrative contexts, it becomes essential to explore how they answer legal questions, and in particular the factors that lead them to decide difficult questions.