{"total":23,"rows":[{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2411.06837","title":"Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications","created":"2024-11-11","cited_by_count":32,"area":null},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2307.05059","title":"On Imperfect Recall in Multi-Agent Influence Diagrams","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2308.16364","title":"Strengthening the EU AI Act: Defining Key Terms on AI Manipulation","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2310.11334","title":"Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2511.04177","title":"When Assisting One Disempowers Another","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.13376","title":"Bounded Minds, Generative Machines: Envisioning Conversational AI that Works with Human Heuristics and Reduces Bias Risk","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2406.09318","title":"Characterising Interventions in Causal Games","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2407.12850","title":"Limits to Predicting Online Speech Using Large Language Models","created":"2024-07-08","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":"2607.28617","title":"AISPA: User-Centric System Prompt Auditing for Large Language Model Applications","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.11794","title":"Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}