Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601. 21700v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations.
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
arXiv:2606. 06356v1 Announce Type: new Abstract: Multimodal generative models produce fluent outputs but remain unreliable when generation must respect structured, domain-specific, or safety-critical knowledge.
arXiv:2606. 05843v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual features from complex, noisy contexts remain opaque.
arXiv:2407. 10486v3 Announce Type: replace Abstract: Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization.
arXiv:2606. 05952v1 Announce Type: cross Abstract: In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios.
arXiv:2512. 15792v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making.
arXiv:2606. 05561v1 Announce Type: cross Abstract: Speech-based mental health screening offers scalable depression detection, yet clinical deployment faces a significant barrier: users' privacy concerns about demographic information exposure.
arXiv:2606. 05748v1 Announce Type: cross Abstract: Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement.
arXiv:2606. 05290v1 Announce Type: cross Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture.
arXiv:2504. 10823v4 Announce Type: replace-cross Abstract: Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios.
arXiv:2605. 25256v2 Announce Type: replace Abstract: Steerable pluralism requires a model to faithfully represent one specified perspective.
arXiv:2606. 05389v1 Announce Type: new Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations.
arXiv:2602. 07739v2 Announce Type: replace-cross Abstract: Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space.
arXiv:2606. 05679v1 Announce Type: cross Abstract: Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users.
arXiv:2604. 00555v5 Announce Type: replace Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level.
arXiv:2601. 21288v2 Announce Type: replace Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain.
arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.
arXiv:2605. 28579v2 Announce Type: replace Abstract: Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design.
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.