{"total":37,"rows":[{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"area":null},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2606.06306","title":"Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness","created":"2026-06-04","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":"2507.23330","title":"AI Must not be Fully Autonomous","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2606.23175","title":"Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2606.13944","title":"LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Values","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2601.10896","title":"DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.20813","title":"Pressure Reveals Character: Behavioural Alignment Evaluation at Depth","created":"2026-02-24","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":"2606.13310","title":"RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.21766","title":"Evaluation Awareness in Language Models: Representation, Verbalization, and Control","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2609.07943","title":"Beliefs and Behavior in Language Models","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2511.21569","title":"AI Identity Disclosure Under Professional Personas: A Gap Between Capacity and Consistency","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2606.27909","title":"Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.20444","title":"Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs","created":"2026-05-12","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":"2609.36139","title":"Language Models Are \"Insecure\" Reporters","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00767","title":"Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.07274","title":"A Trust Layer for Agent Evaluation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16070","title":"Understanding and Reducing Misalignment in Persuasion Optimization","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18541","title":"Empathy Is Not the Scapegoat for Declines in Factuality and Reliability","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}