{"total":13,"rows":[{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"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":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2410.04683","title":"Towards Measuring Goal-Directedness in AI Systems","created":"2024-10-07","cited_by_count":7,"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":"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":"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":"2503.06323","title":"Higher-Order Belief in Incomplete Information MAIDs","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2306.14816","title":"Experiments with Detecting and Mitigating AI Deception","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2406.09318","title":"Characterising Interventions in Causal Games","created":"2024-06-13","cited_by_count":0,"area":null}],"next_cursor":null}