Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2511. 18721v4 Announce Type: replace-cross Abstract: The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict "k-unstable" assumption that rarely holds in practice.
arXiv:2608. 09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on conditions, medications, and geriatric risks that users may omit.
arXiv:2608. 08489v1 Announce Type: new Abstract: Neural network classifiers trained by cross-entropy minimization are highly sensitive to label noise and adversarial contamination.
arXiv:2608. 09654v1 Announce Type: new Abstract: GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on screenshots.
arXiv:2608. 07562v1 Announce Type: cross Abstract: Urban flooding poses an escalating threat to transportation infrastructure, yet no operational system provides real-time, street-level flood-depth estimates at centimeter resolution.
arXiv:2608. 09899v1 Announce Type: new Abstract: In fair ranked link prediction, demographic parity ($\Delta_\mathrm{DP}$) is a common fairness metric.
arXiv:2608. 07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI.
arXiv:2608. 07476v1 Announce Type: new Abstract: We develop a formal framework for constructing canonical interpretations from plural structure theories.
arXiv:2608. 07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.
arXiv:2608. 07525v1 Announce Type: cross Abstract: Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications.
arXiv:2608. 07567v1 Announce Type: cross Abstract: Functional near-infrared spectroscopy (fNIRS) is a promising modality for autism spectrum disorder (ASD) classification, yet existing approaches assume temporally aligned evaluation.
arXiv:2608. 08158v1 Announce Type: new Abstract: Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning.
arXiv:2608. 08220v1 Announce Type: new Abstract: The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial agents that are aligned with human values and that act in ethically acceptable ways.
arXiv:2608. 08284v1 Announce Type: new Abstract: Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing.
arXiv:2608. 08623v1 Announce Type: new Abstract: In Reinforcement Learning with Verifiable Rewards (RLVR) frameworks for mathematical reasoning tasks, floating-point results are typically evaluated using a tolerance-based reward.
arXiv:2608. 08561v1 Announce Type: new Abstract: In medical applications, raw data is frequently associated with significant privacy concerns, lending particular importance to the encoding of summary statistics from the literature.
arXiv:2608. 08881v1 Announce Type: new Abstract: The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deception theories and compared how deception judgments were made relative to baseline models.
arXiv:2608. 07475v1 Announce Type: cross Abstract: Generative Artificial Intelligence (GenAI) presents a governance challenge for STEM assessment.
arXiv:2608. 07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable.
arXiv:2608. 08253v1 Announce Type: new Abstract: AI agents are becoming shared infrastructure, yet durable memory is commonly assembled from separate retrieval, governance, and operational components.