Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2505. 06945v5 Announce Type: replace Abstract: Multimodal data modeling has emerged as a powerful approach in clinical research, enabling the integration of diverse data types such as imaging, genomics, wearable sensors, and electronic health records.
arXiv:2504. 19621v2 Announce Type: replace Abstract: Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since biases may negatively impact generalization performance.
arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.
arXiv:2601. 04641v2 Announce Type: replace-cross Abstract: The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation.
arXiv:2605. 24033v2 Announce Type: replace Abstract: Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations.
arXiv:2310. 19043v3 Announce Type: replace-cross Abstract: Recent years have witnessed growing concerns about the privacy of sensitive data.
arXiv:2607. 07050v3 Announce Type: replace-cross Abstract: Top-K teacher logits make on-policy distillation tractable, but probability mass is not the same as decision support.
arXiv:2607. 25132v2 Announce Type: replace Abstract: A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior.
arXiv:2607. 26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coalition and the required transfers are affordable.
arXiv:2607. 27027v1 Announce Type: new Abstract: Gradient-boosted trees dominate tabular machine learning, yet canonical correlation analysis has always relied on linear or neural encoders.
arXiv:2607. 26397v1 Announce Type: cross Abstract: Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification.
arXiv:2607. 26333v1 Announce Type: cross Abstract: Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment.
arXiv:2607. 26775v1 Announce Type: new Abstract: Many kinds of data have structure along one or more axes: words in a sentence, pixels in an image, nodes in a tree, frames in audio, or cells in a 3D volume.
arXiv:2607. 26792v1 Announce Type: cross Abstract: Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC).
arXiv:2607. 26094v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard approach for aligning large language models with human preferences, but its quality is limited by static, task-agnostic reward models.
Large language models (LLMs) are often compared with the human mind because their decision-making is complex, non-linear and difficult to interpret. Psychological methods developed to investigate unobservable mental processes may therefore help examine LLM behaviour, particularly in government and healthcare.
Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks.
Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost.
As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitoring, the opacity of their spatial judgments limits operator trust and auditability. MLLMs demonstrate strong reasoning but often struggle with fine-grained spatial understanding and object hallucination.
Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers. However, existing image quality assessment (IQA) methods are predominantly designed for natural photographs or AI-generated content, which cannot be directly applied to scientific papers.