{"total":60,"rows":[{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"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":"2601.05752","title":"AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor","created":"2026-01-09","cited_by_count":10,"area":null},{"id":"2601.08648","title":"Safe Language Generation in the Limit","created":"2026-01-13","cited_by_count":9,"area":null},{"id":"2604.19784","title":"Peer-Preservation in Frontier Models","created":"2026-03-30","cited_by_count":9,"area":null},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2603.10028","title":"How to Count AIs: Individuation and Liability for AI Agents","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2603.05786","title":"Proof-of-Guardrail in AI Agents and What (Not) to Trust from It","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2605.21602","title":"Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2605.26438","title":"LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"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":"2607.26654","title":"Constitutional Midtraining: Content Presence Drives Alignment Gains","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2603.00063","title":"Measuring What AI Systems Might Do: Towards A Measurement Science in AI","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2603.23279","title":"Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2512.22725","title":"Mitigating Social Desirability Bias in Random Silicon Sampling","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.08673","title":"Why AI Alignment Failure Is Structural: Learned Human Interaction Structures and AGI as an Endogenous Evolutionary Shock","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2605.29729","title":"Realistic honeypot evaluations for scheming propensity","created":"2026-05-28","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":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.22974","title":"When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.29657","title":"Safety from Honesty in a Disinterested AI Predictor","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2609.32390","title":"Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2510.15395","title":"Corrigibility Transformation: Constructing Goals That Accept Updates","created":"2025-10-17","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":"2603.08024","title":"ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.13236","title":"Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.13378","title":"Do Large Language Models Get Caught in Hofstadter-Mobius Loops?","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.15615","title":"Mechanistic Origin of Moral Indifference in Language Models","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.09128","title":"Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.16872","title":"Some[Body] Must Receive That Pain for Agent Accountability","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.19270","title":"DECOR: Auditing LLM Deception via Information Manipulation Theory","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.08296","title":"Revisiting the shutdown problem","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.12032","title":"Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)","created":"2026-06-10","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":"2606.20610","title":"Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.03478","title":"Demonstrating Generalization Failures via Mixtures of Conditional Policies","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.19292","title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16177","title":"Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.09899","title":"Strangers to Themselves: What Language Models Say About Themselves Is Generic","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10142","title":"Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10724","title":"Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22497","title":"The Wisdom of Artificial Deliberative Crowds","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28274","title":"Shutdown Sabotage Propensities in Multi-Agent Systems","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28335","title":"An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31186","title":"Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32061","title":"Contract monitoring: governing AI via separation of powers","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00371","title":"Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.08670","title":"Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.19342","title":"Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}