Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 19063v1 Announce Type: new Abstract: Objective Structured Clinical Examinations (OSCEs) are the gold standard for assessing clinical competence, yet scoring remains vulnerable to examiner subjectivity, fatigue, and cognitive bias.
arXiv:2607. 19336v1 Announce Type: new Abstract: Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance.
arXiv:2607. 18759v1 Announce Type: new Abstract: Transformers with relative positional encodings often extrapolate to sequences longer than those seen during training, whereas transformers with learned absolute encodings typically do not.
arXiv:2607. 18271v1 Announce Type: new Abstract: Time series forecasts are widely used in decision-critical domains, where they are rarely consumed without accompanying explanations.
arXiv:2607. 18239v1 Announce Type: new Abstract: Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond task requirements is identified as a key driver of Loss of Control (LoC) risk.
arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.
arXiv:2509. 12484v2 Announce Type: replace Abstract: We propose a novel neural network architecture, called Non-Trainable Modification (NTM), for computing Nash equilibria in stochastic differential games (SDGs) on graphs.
arXiv:2605. 03517v4 Announce Type: replace Abstract: Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones.
arXiv:2607. 18845v1 Announce Type: cross Abstract: For decades, ABR has kept two kinds of intelligence apart.
arXiv:2607. 18304v1 Announce Type: new Abstract: The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children.
arXiv:2607. 18259v1 Announce Type: new Abstract: Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to intermediate activations during inference.
arXiv:2607. 18548v1 Announce Type: new Abstract: Agentic artificial intelligence systems, capable of autonomous perception, planning, tool use, and multi-step action, are increasingly proposed for critical engineering domains where decisions carry physical, operational, or economic consequences.
arXiv:2607. 18454v1 Announce Type: cross Abstract: Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling.
arXiv:2607. 18567v1 Announce Type: new Abstract: A graph foundation model generalizes across graph domains by mapping every input into one shared representation before any task reasoning.
arXiv:2607. 18748v1 Announce Type: cross Abstract: This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts.
arXiv:2607. 18785v1 Announce Type: new Abstract: As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution.
arXiv:2607. 18302v1 Announce Type: new Abstract: Autoregressive language models are least accurate at the beginning of a sequence, where little context forces reliance on a generic pretraining prior.
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv:2607. 18470v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals.
arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.