Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens.
arXiv:2606. 21262v2 Announce Type: replace Abstract: Reinforcement learning for multi-step LLM agents often relies on scalar rewards that indicate success but cannot explain why a trajectory is good or bad.
arXiv:2604. 25077v2 Announce Type: replace Abstract: Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak model's blind spots.
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.
arXiv:2607. 20438v1 Announce Type: cross Abstract: Preference-based post-training is usually understood through endpoint behavior, yet the learned update that produces this behavior remains largely opaque.
arXiv:2607. 20890v1 Announce Type: new Abstract: On-device federated learning (FL) enables privacy-preserving and personalized model training on resource-constrained devices such as smartphones and IoT nodes.
arXiv:2607. 21332v1 Announce Type: cross Abstract: Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties.
arXiv:2607. 20925v1 Announce Type: new Abstract: AI knowledge systems require representations of entity importance for retrieval, recommendation, evidence selection, and knowledge-intensive reasoning.
arXiv:2607. 20556v1 Announce Type: new Abstract: In large-scale text analysis tasks, pre-trained language models are often used to embed text corpora for downstream analysis.
arXiv:2607. 20887v1 Announce Type: cross Abstract: Model merging combines independently trained or fine-tuned models, but pairwise alignability does not imply globally consistent alignment.
arXiv:2508. 05502v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally "thin" descriptions in low-resource settings.
arXiv:2605. 05704v3 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution.
arXiv:2607. 20476v1 Announce Type: new Abstract: We present an empirical benchmark evaluating how five large language models assess multisensor physical hazard data.
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
arXiv:2607. 20426v1 Announce Type: cross Abstract: Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models'internal knowledge or have poor cross-domain generalization.
arXiv:2607. 20692v1 Announce Type: cross Abstract: We present a privacy-preserving framework for synthetic lung CT slice generation developed for the Image-CLEFmed GANs 2026 challenge.
arXiv:2607. 21156v1 Announce Type: new Abstract: More than a million people in the UK suffer from frailty or dementia, which severely compromise their ability to travel in urban environments.
arXiv:2607. 21117v1 Announce Type: cross Abstract: Preprocessing blood glucose time-series data is a critical yet often overlooked step in developing data-driven methods for diabetes management, particularly for type 1 diabetes.