{"total":27,"rows":[{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2112.01298","title":"Meaningful human control: actionable properties for AI system development","created":"2021-11-25","cited_by_count":18,"area":null},{"id":"2109.00484","title":"Impossibility Results in AI: A Survey","created":"2021-09-01","cited_by_count":13,"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":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"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":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2205.06905","title":"Perspectives on Incorporating Expert Feedback into Model Updates","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2402.16751","title":"Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2107.13074","title":"Toward AI Assistants That Let Designers Design","created":"2021-07-22","cited_by_count":6,"area":null},{"id":"2311.17165","title":"(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2202.07364","title":"Zero-Shot Assistance in Sequential Decision Problems","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2202.13985","title":"The dangers in algorithms learning humans' values and irrationalities","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2105.07852","title":"Hard Choices and Hard Limits for Artificial Intelligence","created":"2021-05-04","cited_by_count":2,"area":null},{"id":"2402.15821","title":"Cooperation and Control in Delegation Games","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2301.06421","title":"AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents","created":"2023-01-16","cited_by_count":1,"area":null},{"id":"2505.17024","title":"An Affective-Taxis Hypothesis for Alignment and Interpretability","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2606.12502","title":"A Mathematical Theory of Value: a synthesis on goal-directed agency under resource constraints","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.08740","title":"On the Computational Tractability of Robust Bandits","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}