{"total":178,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"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":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"area":null},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2111.06956","title":"Human irrationality: both bad and good for reward inference","created":"2021-11-12","cited_by_count":25,"area":null},{"id":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23,"area":null},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20,"area":null},{"id":"2107.02349","title":"Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections","created":"2021-07-06","cited_by_count":19,"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":"2304.12529","title":"Improved Trust in Human-Robot Collaboration with ChatGPT","created":"2023-04-25","cited_by_count":18,"area":null},{"id":"2306.14858","title":"Proportional Aggregation of Preferences for Sequential Decision Making","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2508.18765","title":"Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement","created":"2025-08-26","cited_by_count":17,"area":null},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16,"area":null},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2103.16033","title":"FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoT","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2405.04495","title":"Toward In-Context Teaching: Adapting Examples to Students' Misconceptions","created":"2024-05-07","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2503.05996","title":"Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners","created":"2025-03-08","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":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2412.05515","title":"Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2503.00940","title":"Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2206.10665","title":"BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2308.11071","title":"Neural Amortized Inference for Nested Multi-agent Reasoning","created":"2023-08-21","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":"2110.00137","title":"Iterative Teacher-Aware Learning","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2111.04698","title":"Interactive Inverse Reinforcement Learning for Cooperative Games","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2207.03470","title":"For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria","created":"2022-07-07","cited_by_count":7,"area":null},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2102.04255","title":"AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks","created":"2021-02-04","cited_by_count":6,"area":null},{"id":"2103.02728","title":"Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agents","created":"2021-03-03","cited_by_count":6,"area":null},{"id":"2104.12582","title":"Understanding and Avoiding AI Failures: A Practical Guide","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2107.13074","title":"Toward AI Assistants That Let Designers Design","created":"2021-07-22","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2303.04257","title":"adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2105.06551","title":"Axes for Sociotechnical Inquiry in AI Research","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5,"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":"2310.20059","title":"Concept Alignment as a Prerequisite for Value Alignment","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2411.17749","title":"The Partially Observable Off-Switch Game","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2509.00117","title":"Embodied AI: Emerging Risks and Opportunities for Policy Action","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2202.07364","title":"Zero-Shot Assistance in Sequential Decision Problems","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2305.17375","title":"Attention Schema in Neural Agents","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2305.17465","title":"Optimization's Neglected Normative Commitments","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","cited_by_count":4,"area":null},{"id":"2412.14741","title":"Active Inference and Human--Computer Interaction","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2412.17797","title":"Observation Interference in Partially Observable Assistance Games","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2502.08864","title":"Off-Switching Not Guaranteed","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2506.22276","title":"Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2106.14611","title":"An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2110.04192","title":"Explaining Reward Functions to Humans for Better Human-Robot Collaboration","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2112.07342","title":"Learning to Guide and to Be Guided in the Architect-Builder Problem","created":"2021-12-14","cited_by_count":3,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2210.00359","title":"Counter-Adversarial Learning with Inverse Unscented Kalman Filter","created":"2022-10-01","cited_by_count":3,"area":null},{"id":"2301.05089","title":"Approximate Information States for Worst-Case Control and Learning in Uncertain Systems","created":"2023-01-12","cited_by_count":3,"area":null},{"id":"2302.09248","title":"Machine Love","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2307.10434","title":"Learning Formal Specifications from Membership and Preference Queries","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2502.14160","title":"Efficient Inverse Multiagent Learning","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","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":"2102.00834","title":"Counterfactual Planning in AGI Systems","created":"2021-01-29","cited_by_count":2,"area":null}],"next_cursor":"100"}