Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools.
arXiv:2604. 11666v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become the engine behind conversational systems, their ability to reason about the intentions and states of their dialogue partners (i.
arXiv:2506. 14092v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions, where choices often involve selecting among competing alternatives.
arXiv:2505. 18672v2 Announce Type: replace Abstract: Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to elicit the aligned and expected behaviors.
arXiv:2607. 21069v1 Announce Type: new Abstract: The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal.
arXiv:2607. 20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question?
arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.
arXiv:2505. 20955v5 Announce Type: replace-cross Abstract: Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues.
arXiv:2607. 21327v1 Announce Type: cross Abstract: Bibliometric indicators - citation counts, h-indexes, co-authorship networks - have long anchored science, technology, and innovation (STI) analytics, yet suffer from temporal lag, semantic shallowness, and an inability to capture the non-linear dynamics of contemporary knowledge ecosystems.
arXiv:2607. 20587v1 Announce Type: cross Abstract: Modern power systems increasingly require probabilistic forecasts amid interacting uncertainties from renewable intermittency, flexible demand, market volatility, and weather-dependent generation.
arXiv:2508. 16947v2 Announce Type: replace-cross Abstract: Despite significant progress, imitation learning-based autonomous driving planners remain largely restricted to reproducing high-frequency biased behaviors, overlooking the inherent behavioral diversity of human driving.
arXiv:2607. 21202v1 Announce Type: cross Abstract: Hybrid MKNF knowledge bases under the well-founded semantics integrate Description Logics with Logic Programming.
arXiv:2607. 20691v1 Announce Type: cross Abstract: Concept Bottleneck Models provide interpretable-by-design predictions by mediating diagnosis through human-understandable concepts, but in medical imaging, their trustworthiness is often limited by the quality and granularity of available supervision.
arXiv:2607. 20581v1 Announce Type: cross Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety.
arXiv:2506. 02897v3 Announce Type: replace Abstract: Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity.
arXiv:2607. 21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions.
arXiv:2607. 20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams.
arXiv:2607. 20696v1 Announce Type: new Abstract: We propose CEDAR (Causal Edge Discovery for Autoregressive Processes), a constraint-based method for lagged causal edge discovery in sparse autoregressive time series.
arXiv:2605. 21514v2 Announce Type: replace-cross Abstract: Diffusion-based information-theoretic approaches provide new theoretical and practical tools to study complex networks.
arXiv:2501. 02211v3 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias generalizes across models, is stable under different inference settings, or depends on how group identity is signaled remains unstudied.