{"list":"other","total":68,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"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":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2010.03950","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","created":"2020-10-06","cited_by_count":191},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","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":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118},{"id":"2310.08118","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","created":"2023-10-12","cited_by_count":108},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105},{"id":"1611.08219","title":"The Off-Switch Game","created":"2016-11-24","cited_by_count":97},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80},{"id":"2006.07532","title":"Online Bayesian Goal Inference for Boundedly-Rational Planning Agents","created":"2020-06-13","cited_by_count":68},{"id":"1809.10756","title":"An Introduction to Probabilistic Programming","created":"2018-09-27","cited_by_count":63},{"id":"1804.04268","title":"Incomplete Contracting and AI Alignment","created":"2018-04-12","cited_by_count":62},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55},{"id":"2102.01685","title":"Agent Incentives: A Causal Perspective","created":"2021-02-02","cited_by_count":51},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50},{"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":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46},{"id":"1512.05832","title":"Learning the Preferences of Ignorant, Inconsistent Agents","created":"2015-12-18","cited_by_count":45},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"1810.09558","title":"An Efficient Bandit Algorithm for Realtime Multivariate Optimization","created":"2018-10-22","cited_by_count":34},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33},{"id":"2405.19479","title":"Participation in the age of foundation models","created":"2024-05-29","cited_by_count":32},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28},{"id":"2208.10687","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types","created":"2022-08-23","cited_by_count":26},{"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},{"id":"2301.12564","title":"A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction","created":"2023-01-29","cited_by_count":22},{"id":"2401.08574","title":"Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability","created":"2024-01-16","cited_by_count":22},{"id":"2403.04471","title":"The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists","created":"2024-03-07","cited_by_count":22},{"id":"1901.08654","title":"The Assistive Multi-Armed Bandit","created":"2019-01-24","cited_by_count":19},{"id":"2106.13249","title":"Modeling the Mistakes of Boundedly Rational Agents Within a Bayesian Theory of Mind","created":"2021-06-24","cited_by_count":19},{"id":"2310.02456","title":"Learning Optimal Advantage from Preferences and Mistaking it for Reward","created":"2023-10-03","cited_by_count":19},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16},{"id":"1811.01267","title":"Legible Normativity for AI Alignment: The Value of Silly Rules","created":"2018-11-03","cited_by_count":15},{"id":"1309.2802","title":"What is Decidable about Partially Observable Markov Decision Processes with {\\omega}-Regular Objectives","created":"2013-09-11","cited_by_count":14},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14},{"id":"1801.04346","title":"A Computational Model of Commonsense Moral Decision Making","created":"2018-01-12","cited_by_count":13},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11},{"id":"2007.09540","title":"Multi-Principal Assistance Games","created":"2020-07-19","cited_by_count":10},{"id":"2209.00692","title":"Making Intelligence: Ethical Values in IQ and ML Benchmarks","created":"2022-09-01","cited_by_count":10},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9},{"id":"2308.00868","title":"Beneficent Intelligence: A Capability Approach to Modeling Benefit, Assistance, and Associated Moral Failures through AI Systems","created":"2023-08-01","cited_by_count":9},{"id":"2402.13956","title":"Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment","created":"2024-02-21","cited_by_count":9},{"id":"1908.01695","title":"Corrigibility with Utility Preservation","created":"2019-08-05","cited_by_count":8},{"id":"2001.04335","title":"Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society","created":"2020-01-13","cited_by_count":7},{"id":"2407.16770","title":"Infinite Ends from Finite Samples: Open-Ended Goal Inference as Top-Down Bayesian Filtering of Bottom-Up Proposals","created":"2024-07-23","cited_by_count":6},{"id":"1412.2993","title":"Algorithmic Rationality: Game Theory with Costly Computation","created":"2014-12-09","cited_by_count":4},{"id":"1912.06594","title":"An Interval-Valued Utility Theory for Decision Making with Dempster-Shafer Belief Functions","created":"2019-12-13","cited_by_count":1}],"next_cursor":null}