Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 06173v2 Announce Type: replace-cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning.
arXiv:2603. 10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning.
arXiv:2502. 12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts.
arXiv:2606. 16368v1 Announce Type: cross Abstract: Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols, both of which lack interpretability.
arXiv:2606. 16707v1 Announce Type: new Abstract: A personalized AI agent needs a user memory: a persistent model of who the user is, built across many conversations and consulted on each new one.
arXiv:2606. 16304v1 Announce Type: new Abstract: Federated unlearning (FU) enables the removal of specific data contributions from federated learning (FL) models to comply with regulations such as the General Data Protection Regulation (GDPR).
arXiv:2606. 14791v1 Announce Type: cross Abstract: Self-supervised learning advances audio representation for multimedia analysis.
arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.
arXiv:2504. 11775v3 Announce Type: replace-cross Abstract: Fairness has become an important concern in insurance pricing as insurers increasingly rely on machine learning models to predict expected losses.
arXiv:2606. 15940v1 Announce Type: new Abstract: Synthetic and distilled student data are increasingly used to enable privacy-conscious learning analytics, yet their suitability for decision-facing institutional support remains uncertain.
arXiv:2606. 15766v1 Announce Type: new Abstract: A central pedagogical value evaluated in AI tutor benchmarks is scaffolding: guiding students through graduated steps toward a solution.
arXiv:2606. 15756v1 Announce Type: cross Abstract: Lane-change prediction is a central task in intelligent vehicles, where early maneuver anticipation can support safer decision-making.
arXiv:2606. 16175v1 Announce Type: new Abstract: Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events.
arXiv:2606. 15077v1 Announce Type: new Abstract: We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries.
arXiv:2606. 15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive.
arXiv:2606. 16190v1 Announce Type: cross Abstract: Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints.
arXiv:2602. 05060v2 Announce Type: replace Abstract: Cybergrooming is an evolving threat to youth, requiring proactive educational interventions.
arXiv:2606. 15331v1 Announce Type: cross Abstract: Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective.
arXiv:2606. 14765v1 Announce Type: cross Abstract: Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning.
arXiv:2606. 15655v1 Announce Type: new Abstract: The need for effective cattle identification technology is now more acutely felt than ever in maintaining biosecurity, food safety, and supply chain efficacy in livestock management.