{"total":21,"rows":[{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"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":"2405.04325","title":"Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation","created":"2024-05-07","cited_by_count":10,"area":null},{"id":"2509.20393","title":"The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"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":"2405.12999","title":"An Assessment of Model-On-Model Deception","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2412.17797","title":"Observation Interference in Partially Observable Assistance Games","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2410.00258","title":"Possible Principles for Aligned Structure Learning Agents","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2506.16150","title":"PRISON: Unmasking the Criminal Potential of Large Language Models","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2405.16588","title":"Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2503.06323","title":"Higher-Order Belief in Incomplete Information MAIDs","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2410.04272","title":"Evaluating Language Model Character Traits","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2606.05330","title":"A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.11053","title":"Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}