Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 15419v1 Announce Type: cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA).
arXiv:2507. 02288v2 Announce Type: replace-cross Abstract: Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains.
arXiv:2606. 15447v1 Announce Type: new Abstract: Electronic health record foundation models typically treat ICD diagnosis codes as flat tokens, overlooking the clinically meaningful hierarchical structure that captures disease families, subcategories, and fine-grained diagnostic detail.
arXiv:2606. 15314v1 Announce Type: cross Abstract: Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take.
arXiv:2606. 15284v1 Announce Type: cross Abstract: Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support.
arXiv:2606. 15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks.
arXiv:2606. 17035v1 Announce Type: new Abstract: Prior research suggests that differential privacy (DP) inherently enhances the robustness of federated learning (FL) against backdoor attacks.
arXiv:2606. 15024v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions.
arXiv:2606. 16595v1 Announce Type: cross Abstract: Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2502. 05163v2 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) necessitates effective mechanisms to ensure their responsible deployment by accurately distinguishing unsafe content from benign content.
arXiv:2604. 17301v2 Announce Type: replace-cross Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances.
arXiv:2606. 15199v1 Announce Type: new Abstract: Proactive warning is an important capability for edge intelligent services, where the system predicts whether a subject will successfully complete an incoming task under strict latency and privacy constraints.
arXiv:2512. 15313v2 Announce Type: replace-cross Abstract: Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems.
arXiv:2606. 15479v1 Announce Type: cross Abstract: Steerable convolutional neural networks (Steerable-CNNs) guarantee SE(3)-equivariance by parameterizing kernels as linear combinations of steerable basis functions, but their deterministic nature precludes uncertainty quantification - limiting their use in settings where confidence estimates are essential.
arXiv:2512. 10104v2 Announce Type: cross Abstract: Email phishing is one of the most prevalent and globally consequential vectors of cyber intrusion.
arXiv:2606. 16127v1 Announce Type: cross Abstract: The worldwide surge of authoritarianism, combined with the increasing central role in users' everyday lives, raises the question of to what extent specific models exhibit or promote authoritarian attitudes and characteristics.
arXiv:2606. 15573v1 Announce Type: new Abstract: In agentic systems, human-generated data records anchor the value of AI services.
arXiv:2606. 16278v1 Announce Type: cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale.
arXiv:2606. 15250v1 Announce Type: cross Abstract: Radiographic assessment of lower-limb alignment (LLA) is important for predicting joint health and surgical outcomes in total knee arthroplasty.