Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 06869v1 Announce Type: new Abstract: Aim: Existing AI-assisted traditional Chinese medicine diagnostic tools suffer from opaque reasoning processes, passive interaction, and limited treatment plan presentation.
arXiv:2606. 07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models.
arXiv:2606. 06861v1 Announce Type: cross Abstract: Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability.
arXiv:2606. 06735v1 Announce Type: new Abstract: Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior.
arXiv:2606. 07196v1 Announce Type: new Abstract: Classical sparse Type-II Bayesian methods for M/EEG brain imaging support joint estimation of source and noise hyperparameters, but rely on fixed iterative update rules.
arXiv:2606. 06903v1 Announce Type: cross Abstract: Human image animation aims to generate a video from a static reference image, guided by pose information extracted from a driving video.
arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.
arXiv:2606. 06804v1 Announce Type: new Abstract: Digital learning environments record learners' responses to individual items, making it possible to study the development of specific skills rather than overall scores.
arXiv:2606. 06825v1 Announce Type: cross Abstract: Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state.
arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv:2312. 07762v3 Announce Type: replace Abstract: Psychiatry research seeks to understand the manifestations of psychopathology in behavior, as measured in questionnaire data, by identifying a small number of latent factors that explain them.
arXiv:2606. 06563v1 Announce Type: cross Abstract: Software testing is critical for verifying that systems meet specified requirements, yet remains among the most time-consuming and expensive activities in development.
arXiv:2606. 07515v1 Announce Type: cross Abstract: We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems.
arXiv:2508. 02039v2 Announce Type: replace Abstract: Increasing concerns for data privacy and other difficulties associated with retrieving source data for model training have created the need for source-free transfer learning, in which one only has access to pre-trained models instead of data from the original source domains.
arXiv:2606. 07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space.
arXiv:2606. 07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.
arXiv:2606. 06830v1 Announce Type: cross Abstract: Data-driven pricing is increasingly prevalent in sectors such as airlines, lending, insurance, and retail.
arXiv:2606. 07093v1 Announce Type: new Abstract: The fertility trend in developing countries has experienced a significant decline in the last few decades; at the same time, the role of women in the workplace has improved.
arXiv:2605. 01642v2 Announce Type: replace Abstract: Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time.
arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.