Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 18989v1 Announce Type: cross Abstract: Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable.
arXiv:2606. 18726v1 Announce Type: cross Abstract: Structurally constrained event sequence generation remains challenging because generated paths must preserve transition feasibility, temporal order, termination, and attribute consistency.
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
arXiv:2606. 18864v1 Announce Type: cross Abstract: This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints.
arXiv:2606. 19259v1 Announce Type: cross Abstract: Text-rich images often contain privacy-sensitive, transactional, or decision-relevant information.
arXiv:2605. 07022v3 Announce Type: replace Abstract: Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage.
arXiv:2606. 18506v1 Announce Type: new Abstract: Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue.
arXiv:2512. 09185v4 Announce Type: replace-cross Abstract: Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment.
arXiv:2606. 19152v1 Announce Type: cross Abstract: Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computationally prohibitive.
arXiv:2601. 12805v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks.
arXiv:2606. 18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local.
arXiv:2606. 18801v1 Announce Type: cross Abstract: With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access.
arXiv:2606. 18257v1 Announce Type: cross Abstract: While LLMs show promise in automating educational content creation, their ability to generate questions that stimulate higher-order thinking remains understudied.
arXiv:2606. 18993v1 Announce Type: cross Abstract: Testing conditional independence is fundamental yet intrinsically difficult: without additional assumptions, Type I error control is impossible in general.
arXiv:2606. 18567v1 Announce Type: cross Abstract: This paper presents a methodology-centered transfer learning framework for fragility adaptation under domain shift, class imbalance, and scarce target labels while preserving engineering interpretability and supporting decision-making under uncertainty.
arXiv:2606. 18661v1 Announce Type: cross Abstract: Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios.
arXiv:2606. 19212v1 Announce Type: cross Abstract: Recent empirical work shows that semantically equivalent paraphrases can fool financial sentiment classifiers: although a paraphrase remains close to the original under a strong reference embedding, it may shift the target model's representation enough to change the predicted class.
arXiv:2603. 04895v2 Announce Type: replace-cross Abstract: Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima.
arXiv:2606. 19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs.
arXiv:2606. 19168v1 Announce Type: new Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms.