{"list":"other","total":57,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2002.06673","title":"Performative Prediction","created":"2020-02-16","cited_by_count":327},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"2002.04833","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","created":"2020-02-12","cited_by_count":120},{"id":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2402.14740","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","created":"2024-02-22","cited_by_count":108},{"id":"2404.16244","title":"The Ethics of Advanced AI Assistants","created":"2024-04-24","cited_by_count":107},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92},{"id":"1804.04268","title":"Incomplete Contracting and AI Alignment","created":"2018-04-12","cited_by_count":62},{"id":"2303.06135","title":"Rewarding Chatbots for Real-World Engagement with Millions of Users","created":"2023-03-10","cited_by_count":59},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53},{"id":"1906.09624","title":"On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference","created":"2019-06-23","cited_by_count":49},{"id":"1811.00260","title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","created":"2018-11-01","cited_by_count":48},{"id":"1512.05832","title":"Learning the Preferences of Ignorant, Inconsistent Agents","created":"2015-12-18","cited_by_count":45},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"2009.09153","title":"Hidden Incentives for Auto-Induced Distributional Shift","created":"2020-09-19","cited_by_count":43},{"id":"2203.17232","title":"Performative Power","created":"2022-03-31","cited_by_count":43},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"1806.01186","title":"Penalizing side effects using stepwise relative reachability","created":"2018-06-04","cited_by_count":38},{"id":"2009.13649","title":"The EMPATHIC Framework for Task Learning from Implicit Human Feedback","created":"2020-09-28","cited_by_count":38},{"id":"2110.11010","title":"Algorithmic Amplification of Politics on Twitter","created":"2021-10-21","cited_by_count":38},{"id":"1902.04198","title":"Preferences Implicit in the State of the World","created":"2019-02-12","cited_by_count":34},{"id":"2006.04948","title":"AI Research Considerations for Human Existential Safety (ARCHES)","created":"2020-05-30","cited_by_count":33},{"id":"2303.08721","title":"Artificial Influence: An Analysis Of AI-Driven Persuasion","created":"2023-03-15","cited_by_count":33},{"id":"1810.05903","title":"Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility","created":"2018-10-13","cited_by_count":32},{"id":"2305.16941","title":"Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media","created":"2023-05-26","cited_by_count":30},{"id":"2202.11776","title":"The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization","created":"2022-02-23","cited_by_count":29},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25},{"id":"2402.07221","title":"The Reasons that Agents Act: Intention and Instrumental Goals","created":"2024-02-11","cited_by_count":23},{"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},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20},{"id":"2301.02324","title":"Reasoning about Causality in Games","created":"2023-01-05","cited_by_count":20},{"id":"1901.08654","title":"The Assistive Multi-Armed Bandit","created":"2019-01-24","cited_by_count":19},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17},{"id":"2302.01724","title":"Reinforcing User Retention in a Billion Scale Short Video Recommender System","created":"2023-02-03","cited_by_count":15},{"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},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7},{"id":"2302.11225","title":"The Amplification Paradox in Recommender Systems","created":"2023-02-22","cited_by_count":6},{"id":"2402.06831","title":"What We Know About Using Non-Engagement Signals in Content Ranking","created":"2024-02-09","cited_by_count":6},{"id":"2310.11840","title":"On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning","created":"2023-10-18","cited_by_count":5},{"id":"2011.02544","title":"Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies","created":"2020-11-04","cited_by_count":3},{"id":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2}],"next_cursor":null}