Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 08689v1 Announce Type: new Abstract: The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error.
arXiv:2603. 00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood.
arXiv:2406. 14373v3 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv:2608. 07786v1 Announce Type: new Abstract: Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ownership, and evolution.
arXiv:2608. 07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures.
arXiv:2604. 23859v2 Announce Type: replace Abstract: With spotforecast2-safe we present an integrated Compliance-by-Design approach to Python-based point forecasting of time series in safety-critical environments.
arXiv:2608. 09082v1 Announce Type: new Abstract: Spatiotemporal prediction on graph-structured data is central to traffic forecasting and environmental monitoring, yet decentralized and heterogeneous data complicate both sequence modeling and collaborative training.
arXiv:2512. 07195v2 Announce Type: replace-cross Abstract: Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual without cross-lingual interaction, an essential property of real societies.
arXiv:2608. 07651v1 Announce Type: new Abstract: Large language models (LLMs) show promise in medical image interpretation but suffer from hallucination, limited accuracy, and run-to-run inconsistency.
arXiv:2608. 09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints.
arXiv:2608. 09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.
arXiv:2608. 08736v1 Announce Type: new Abstract: Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain underexplored.
arXiv:2608. 07808v1 Announce Type: cross Abstract: Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis.
arXiv:2608. 09025v1 Announce Type: new Abstract: Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy.
arXiv:2603. 12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.
arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.
arXiv:2605. 18414v2 Announce Type: replace-cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries.
arXiv:2512. 07901v4 Announce Type: replace-cross Abstract: Von Neumann founded both game theory and the theory of self-reproducing automata, but the two programs never merged.
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).