Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 28674v1 Announce Type: new Abstract: Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque.
arXiv:2607. 28685v1 Announce Type: new Abstract: Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety.
arXiv:2607. 29077v1 Announce Type: new Abstract: Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obtain a desired output.
arXiv:2607. 29431v1 Announce Type: new Abstract: Large language models increasingly generate optimization models from natural language, but existing evaluation often reduces a generated model and its ground truth to a single equivalent/not-equivalent verdict or an execution-success rate--labels that are neither independently checkable nor faithful to the multiple distinct senses in which two formulations can agree.
arXiv:2607. 28630v1 Announce Type: cross Abstract: Generative AI (GenAI) holds significant promise for advancing educational equity among ethnic minority students by broadening access to learning resources and mitigating linguistic barriers.
arXiv:2607. 28647v1 Announce Type: cross Abstract: This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement.
arXiv:2607. 28650v1 Announce Type: cross Abstract: While industry discourse often emphasizes immediate productivity gains and frames GenAI primarily as a tool for automation, the integration of GenAI into system administration may involve deeper shifts in professional practice that are not yet fully understood.
arXiv:2607. 28890v1 Announce Type: cross Abstract: Evaluations of LLM-assisted qualitative coding almost universally measure model performance as agreement with human coders, a practice that presumes human coding is the standard to approximate.
arXiv:2607. 28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender.
arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
arXiv:2607. 29071v1 Announce Type: cross Abstract: Federated learning of foundation models faces a fundamental resource-asymmetry challenge: the institutions holding the most valuable domain-specific data cannot host billion-parameter models.
arXiv:2607. 29144v1 Announce Type: cross Abstract: Synthetic face datasets are increasingly used to reduce privacy exposure and data access constraints in biometric recognition.
arXiv:2607. 29334v1 Announce Type: cross Abstract: Conversational AI developed by geopolitical rivals reaches citizens worldwide, raising concerns that it could sway public opinion or be rejected as foreign propaganda, with consequences for democratic discourse and information sovereignty.
arXiv:2607. 29353v1 Announce Type: cross Abstract: With the ever-increasing pervasiveness of smart edge devices, the demand is growing for applications that can be tailored to users (e.
arXiv:2607. 29394v1 Announce Type: cross Abstract: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for breast cancer management, but reliance on gadolinium-based contrast agents (GBCAs) restricts use in contraindicated populations, prolongs scan protocols, and presents environmental toxicity concerns.
arXiv:2607. 29445v1 Announce Type: cross Abstract: Infrared vision-language models (IR-VLMs) extend thermal perception to open-vocabulary classification, image captioning, and visual question answering.
arXiv:2601. 02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning.
arXiv:2607. 28698v1 Announce Type: new Abstract: Flow matching assumes fully observed training data, which many real-world applications rarely provide.
arXiv:2607. 28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication.