Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL).
arXiv:2606. 05183v2 Announce Type: replace-cross Abstract: Pass/fail safety evaluation reports whether a model refused.
arXiv:2608. 14570v1 Announce Type: new Abstract: Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning.
arXiv:2608. 14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant.
arXiv:2608. 14657v1 Announce Type: new Abstract: Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and their inability to leverage structured clinical knowledge.
arXiv:2608. 15036v1 Announce Type: new Abstract: The Lipschitz bandit problem extends the traditional multi-armed bandit framework to continuous action spaces by assuming that the reward functions satisfy a Lipschitz condition.
arXiv:2608. 15815v1 Announce Type: new Abstract: WiFi Channel State Information (CSI) has emerged as a privacy-preserving alternative to cameras for human pose estimation.
arXiv:2608. 16710v1 Announce Type: new Abstract: As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle not only safety-critical locomotion but also their subsequent moral weight.
arXiv:2608. 16804v1 Announce Type: new Abstract: Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking.
arXiv:2608. 16776v1 Announce Type: new Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant.
arXiv:2608. 16134v1 Announce Type: new Abstract: In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges.
arXiv:2608. 16031v1 Announce Type: new Abstract: Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections.
arXiv:2608. 15578v1 Announce Type: cross Abstract: Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that is difficult to expose with text-only red-teaming.
arXiv:2608. 15673v1 Announce Type: cross Abstract: Large language model guardrails can be viewed as policy-consistency problems: a system must determine which policy-relevant facts hold in a prompt-response pair and what those facts imply under a given policy.
arXiv:2608. 15266v1 Announce Type: cross Abstract: Functional connectome analysis examines brain-region interactions to understand and identify disorders such as autism spectrum disorder and Alzheimer's disease.
arXiv:2608. 15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.
arXiv:2608. 16349v1 Announce Type: new Abstract: Large language model (LLM) agents may assist flight crews with complex decisions and task execution, but existing aviation evaluations centered on static knowledge do not support systematic testing of procedural execution and safety compliance in interactive environments.
arXiv:2608. 15129v1 Announce Type: cross Abstract: We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages.
arXiv:2608. 15311v1 Announce Type: new Abstract: Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing.
arXiv:2608. 15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.