{"total":19,"rows":[{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2205.13619","title":"Fairness in Recommendation: Foundations, Methods and Applications","created":"2022-05-26","cited_by_count":27,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2401.07836","title":"Two Types of AI Existential Risk: Decisive and Accumulative","created":"2024-01-15","cited_by_count":22,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2203.10525","title":"Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI","created":"2022-03-20","cited_by_count":12,"area":null},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2202.11629","title":"A Complete Criterion for Value of Information in Soluble Influence Diagrams","created":"2022-02-23","cited_by_count":5,"area":null},{"id":"2406.06736","title":"Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2507.16829","title":"You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2304.14553","title":"Appropriateness is all you need!","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2506.23952","title":"Autonomy by Design: Preserving Human Autonomy in AI Decision-Support","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2209.11801","title":"Solutions to preference manipulation in recommender systems require knowledge of meta-preferences","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2209.13021","title":"Inclusive Ethical Design for Recommender Systems","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2503.03401","title":"Evolutionary Prediction Games","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null}],"next_cursor":null}