{"total":74,"rows":[{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2508.09224","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training","created":"2025-08-12","cited_by_count":52,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","cited_by_count":14,"area":null},{"id":"2509.21651","title":"Can AI Perceive Physical Danger and Intervene?","created":"2025-09-25","cited_by_count":14,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2510.07686","title":"Stress-Testing Model Specs Reveals Character Differences among Language Models","created":"2025-10-09","cited_by_count":13,"area":null},{"id":"2502.14828","title":"Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2507.03772","title":"Skewed Score: A statistical framework to assess autograders","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2508.05432","title":"Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI","created":"2025-08-07","cited_by_count":6,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2602.04811","title":"SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2503.04736","title":"Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2505.00174","title":"Real-World Gaps in AI Governance Research","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2512.06393","title":"Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors","created":"2025-12-06","cited_by_count":5,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2605.30803","title":"PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2505.13577","title":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.15242","title":"Adaptive Plan-Execute Framework for Smart Contract Security Auditing","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.21929","title":"Libra: Large Chinese-based Safeguard for AI Content","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2510.26935","title":"RepV: Safety-Separable Latent Spaces for Scalable Neurosymbolic Plan Verification","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.11986","title":"Learning to Extract Context for Context-Aware LLM Inference","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2605.24229","title":"How Well Do Models Follow Their Constitutions?","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2608.02684","title":"A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2508.11534","title":"Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2601.23094","title":"Safer Policy Compliance with Dynamic Epistemic Fallback","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.01187","title":"Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2603.08760","title":"Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.04413","title":"(Mis)generalization of Helpful-only Fine-tuning","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.09475","title":"Emergent alignment and the projectability of ethical personas","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.21063","title":"QuantiBias: Benchmarking Quantization-Induced Bias in LLMs","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.26173","title":"Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.03070","title":"AI Security Leaderboard: Methodology, Results and Minimal Standard","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.09828","title":"Multi-Agent AI Safety as an Institutional Design Problem","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.18027","title":"Chain-of-Experience for Continual LLM Improvement","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.23264","title":"Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2503.00224","title":"\\`A la recherche du sens perdu: your favourite LLM might have more to say than you can understand","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.10108","title":"Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.11834","title":"Don't Walk the Line: Boundary Guidance for Filtered Generation","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.19115","title":"AI Consciousness and Existential Risk","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.06816","title":"\"Dark Triad\" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.01354","title":"Open-Domain Safety Policy Construction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.16654","title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.30521","title":"Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.13739","title":"A Virtuous AI is an Existential Risk","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.05407","title":"Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.13162","title":"What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.04347","title":"Introspecting Alignment Shifts Beyond Behaviors Implanted Through Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06578","title":"From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.12372","title":"Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.01275","title":"The Constitutional Coverage Trilemma in AI Governance","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07627","title":"Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.10883","title":"Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.29837","title":"PUBG Ally: A Conversational Embodied Agent as an AI Teammate","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38093","title":"Character Training for Risk-Averse Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19948","title":"When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}