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. 19061v1 Announce Type: cross Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems.
arXiv:2607. 18258v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics.
arXiv:2607. 19317v1 Announce Type: new Abstract: Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning.
arXiv:2607. 18479v1 Announce Type: new Abstract: Malicious anomalous activity detection is a fundamental challenge for cyber security systems.
arXiv:2607. 18291v1 Announce Type: cross Abstract: Time-dependent reliability analysis is crucial for ensuring the long-term safety and performance of engineering systems under uncertainties.
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. 18292v1 Announce Type: cross Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability.
arXiv:2607. 18573v1 Announce Type: new Abstract: Delay-risk models are usually judged by predictive accuracy.
arXiv:2607. 18536v1 Announce Type: new Abstract: Macro placement still requires substantial manual refinement in industrial physical design flows.
arXiv:2607. 18665v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance.
arXiv:2607. 19096v1 Announce Type: new Abstract: Agent-memory workloads mix direct factual lookup, relation-chain and current-state reasoning, and broad synthesis over long histories.
arXiv:2606. 12442v2 Announce Type: replace-cross Abstract: At present, loss of control risks have gained much prominence in public discussion, particularly in relation to AI, with extensive discourse present among academics, frontier labs, and even governments.
arXiv:2607. 18755v1 Announce Type: new Abstract: Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings.
arXiv:2607. 18847v1 Announce Type: cross Abstract: Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks.
arXiv:2607. 18704v1 Announce Type: cross Abstract: Caption Studio is a transparency-first speech and audio intelligence platform that transforms spoken audio and video into structured, searchable content through automated transcription, speaker diarization, speech analytics, signal-level audio analysis, and subtitle generation.
arXiv:2603. 16410v2 Announce Type: replace-cross Abstract: Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character development, pacing, tone consistency, and emotional progression.