Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 01039v3 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.
arXiv:2602. 24287v2 Announce Type: replace-cross Abstract: In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses.
arXiv:2510. 04399v3 Announce Type: replace Abstract: We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes.
arXiv:2608. 10964v1 Announce Type: cross Abstract: Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these models suffer from $\textit{confidence miscalibration}$---a systematic gap between expressed certainty and actual diagnostic accuracy that undermines clinical trust.
arXiv:2608. 10513v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones.
arXiv:2608. 10339v1 Announce Type: cross Abstract: Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to estimate and rank the causal effects of such interventions.
arXiv:2608. 10279v1 Announce Type: cross Abstract: Streaming language-model output creates a release-timing problem: complete-response moderation acts after streamed text has escaped, whereas repeated semantic classification of partial text can be costly and unstable.
arXiv:2608. 10056v1 Announce Type: cross Abstract: Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians and obstacles.
arXiv:2608. 10344v1 Announce Type: cross Abstract: Thermo-mechanical compliant devices are commonly designed with small-strain linear elasticity and temperature-independent material properties, even though they might operate hundreds of kelvin above ambient where both assumptions are questionable.
arXiv:2608. 10042v1 Announce Type: cross Abstract: Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level personalization.
arXiv:2608. 09972v1 Announce Type: cross Abstract: First-generation AI weather models are often reported to underperform at extremes, mostly in reanalysis-based evaluations of deterministic regression systems.
arXiv:2608. 09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure behind visual layout.
arXiv:2608. 10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time.
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
arXiv:2310. 15976v4 Announce Type: replace Abstract: signSGD is attractive in nonconvex optimization because it communicates sign-valued rather than full-precision gradients.
arXiv:2509. 23413v3 Announce Type: replace Abstract: Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a single model.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv:2601. 22012v3 Announce Type: replace Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms.
arXiv:2512. 06227v3 Announce Type: replace-cross Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky behaviours for online safety, yet labelling such information is often costly and/or difficult due to its multi-label and dynamic nature.
arXiv:2509. 05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior?