Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv:2607. 03593v1 Announce Type: cross Abstract: Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, characterization, prognosis, and treatment planning.
arXiv:2607. 05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negotiate with services.
arXiv:2607. 05251v1 Announce Type: cross Abstract: Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints.
arXiv:2510. 16923v3 Announce Type: replace-cross Abstract: Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.
arXiv:2211. 15590v2 Announce Type: replace Abstract: Analyzing the behavior of complex interdependent networks requires complete information about the network topology and the interdependent links across networks.
arXiv:2605. 28543v2 Announce Type: replace Abstract: LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness.
arXiv:2607. 02575v1 Announce Type: cross Abstract: Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the support set for task induction.
arXiv:2507. 04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods.
arXiv:2607. 04072v1 Announce Type: cross Abstract: Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user.
arXiv:2607. 03190v1 Announce Type: cross Abstract: Scenario-based transportation analysis specifies future assumptions through aggregate population targets, whereas generative population synthesis models produce detailed individual-level realizations.
arXiv:2607. 04290v1 Announce Type: cross Abstract: Large Language Models (LLMs) are proposed as control interfaces for next-generation networks, but their latency, hallucinations, and lack of control guarantees make them unsuitable for near-real-time packet schedulers, especially in dynamic V2X environments.
arXiv:2607. 03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates.
arXiv:2508. 10031v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks.
arXiv:2607. 04729v1 Announce Type: cross Abstract: LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace.
arXiv:2607. 03386v1 Announce Type: new Abstract: Agentic AI systems are increasingly used to edit, refine, and repair decision policies, but evaluating these edits is difficult when per-state expert action labels are unavailable.
arXiv:2512. 22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings.
arXiv:2607. 04726v1 Announce Type: cross Abstract: Chart-to-code generation is commonly trained with supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target.
arXiv:2607. 03325v1 Announce Type: cross Abstract: We present an automated pipeline that decomposes Italian tax-court judgments into individual legal issues and extracts, for each issue, a structured XML representation grounded in the IRAC framework and the legal syllogism.
arXiv:2603. 06921v2 Announce Type: replace-cross Abstract: Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments.