Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 30851v1 Announce Type: cross Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL.
arXiv:2606. 30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements.
arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.
arXiv:2606. 31272v1 Announce Type: cross Abstract: AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents.
arXiv:2606. 31253v1 Announce Type: cross Abstract: The classical $k$-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing values.
arXiv:2606. 30788v1 Announce Type: new Abstract: Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities.
arXiv:2606. 31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method.
arXiv:2605. 27756v2 Announce Type: replace-cross Abstract: Linear dimensionality reduction methods such as proper orthogonal decomposition (POD) make high-dimensional data amenable to analysis by identifying the principal components, or modes, that capture the most variance, or energy, in the data and constructing a low-dimensional representation in the subspace they span.
arXiv:2606. 31334v1 Announce Type: new Abstract: Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives.
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv:2606. 30702v1 Announce Type: cross Abstract: Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demographic oversampling, and subgroup fairness.
arXiv:2507. 07109v2 Announce Type: cross Abstract: The VAMOS++ magnetic spectrometer is a multi-parametric system that integrates ion optical magnetic elements with a multi-detector stack.
arXiv:2606. 31282v1 Announce Type: new Abstract: Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization.
arXiv:2606. 31074v1 Announce Type: cross Abstract: Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics.
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.
arXiv:2606. 31603v1 Announce Type: cross Abstract: Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.
arXiv:2606. 31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems.
arXiv:2606. 30836v1 Announce Type: new Abstract: Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between high-dimensional decision variables and objective outcomes increasingly opaque.
arXiv:2606. 23375v2 Announce Type: replace-cross Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated risks have emerged.
arXiv:2606. 31045v1 Announce Type: new Abstract: Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory environments remains challenging.