Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.00411v1 Announce Type: new Abstract: Modern face recognition (FR) owes much of its success to deep neural networks that learn to extract compact identity embeddings from face images. These...
arXiv:2502.03726v3 Announce Type: replace Abstract: Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these...
arXiv:2605.28456v2 Announce Type: replace Abstract: Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on vis...
arXiv:2505.12781v5 Announce Type: replace-cross Abstract: Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models...
arXiv:2601.01972v5 Announce Type: replace-cross Abstract: State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, the...
arXiv:2609.00361v1 Announce Type: cross Abstract: Toxic language in digital workplaces such as pejoratives, sarcasm, condescension, and subtle incivility can erode trust, morale, and collaboration. E...
arXiv:2508.04698v2 Announce Type: replace Abstract: LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Rec...
arXiv:2609.00189v1 Announce Type: new Abstract: Goal-directed optimization is essential for steering molecular generators to propose candidates with desired properties. However, it is often implement...
arXiv:2609.00518v1 Announce Type: new Abstract: Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design...
arXiv:2609.01343v1 Announce Type: new Abstract: Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating archit...
arXiv:2609.01129v1 Announce Type: new Abstract: We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under compos...
arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic a...
arXiv:2609.00015v1 Announce Type: new Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, control...
arXiv:2609.00071v1 Announce Type: new Abstract: Prediction error is widely used to evaluate nuisance-function estimators in causal inference, but its relationship with causal estimator performance ma...
arXiv:2609.00100v1 Announce Type: new Abstract: Psychometric questionnaires contain rich item-level information, yet it remains unclear whether different representation learning objectives recover th...
arXiv:2609.00304v1 Announce Type: new Abstract: Models express values and welfare-relevant self-reports, but it is unclear whether these outputs reflect stable preferences or a stable self. We thus i...
arXiv:2609.00513v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex...
arXiv:2609.00578v1 Announce Type: new Abstract: Large Language Models (LLMs) can solve complex problems, but their misuse in high-risk domains can lead to severe consequences. Model providers therefo...
arXiv:2609.00014v1 Announce Type: cross Abstract: Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid,...
arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...