Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions.
arXiv:2605. 16411v2 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling.
arXiv:2608. 06195v1 Announce Type: cross Abstract: Probabilistic Regression Trees (PRTrees) are a smooth and consistent alternative to classical regression trees, producing continuous predictions through probabilistic split assignments.
arXiv:2608. 06246v1 Announce Type: new Abstract: Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning.
arXiv:2608. 05163v1 Announce Type: cross Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information.
arXiv:2608. 05158v1 Announce Type: cross Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential functions for survival.
arXiv:2607. 28609v2 Announce Type: replace Abstract: Computer-using agents (CUAs) are advancing rapidly across the digital world.
arXiv:2608. 05892v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems.
arXiv:2608. 05418v1 Announce Type: new Abstract: AI tools are being increasingly adopted in policing in the UK and worldwide.
arXiv:2608. 06123v1 Announce Type: new Abstract: Measuring political bias in large language models (LLMs) remains challenging as it can manifest through subtle differences in framing, argumentation, and legal reasoning that are difficult to capture with a single metric.
arXiv:2608. 06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
arXiv:2608. 05602v1 Announce Type: new Abstract: Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled.
arXiv:2608. 06112v1 Announce Type: new Abstract: Hospitals are rapidly adopting artificial intelligence for triage, imaging, scheduling etc.
arXiv:2608. 06351v1 Announce Type: new Abstract: This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation.
arXiv:2608. 05188v1 Announce Type: cross Abstract: Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy"), exhibit incomplete logical generalization, and produce confident but incorrect responses.
arXiv:2608. 05210v1 Announce Type: cross Abstract: Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}.
arXiv:2608. 06265v1 Announce Type: new Abstract: Synthetic clinical benchmarks for enterprise AI agents can pass existing utility checks and still remain structurally unrealistic, especially in privacy-sensitive healthcare settings where operational data are hard to access.
arXiv:2608. 05715v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-language commands into executable actions grounded in visual scene understanding.
arXiv:2608. 06105v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requires reward models that are interpretable and robust to changing environments.
arXiv:2608. 06179v1 Announce Type: new Abstract: Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations.