{"total":120,"rows":[{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75,"area":"offlinerl"},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50,"area":null},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"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":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41,"area":"alignment"},{"id":"2404.09824","title":"Impact of Preference Noise on the Alignment Performance of Generative Language Models","created":"2024-04-15","cited_by_count":41,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"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":"2212.03201","title":"Misspecification in Inverse Reinforcement Learning","created":"2022-12-06","cited_by_count":27,"area":"offlinerl"},{"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,"area":"alignment"},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","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":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"id":"2211.06519","title":"The Expertise Problem: Learning from Specialized Feedback","created":"2022-11-12","cited_by_count":20,"area":"alignment"},{"id":"2207.03395","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction","created":"2022-07-07","cited_by_count":19,"area":"offlinerl"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2306.16207","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","created":"2023-06-28","cited_by_count":17,"area":"agents"},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2205.07886","title":"An Empirical Investigation of Representation Learning for Imitation","created":"2022-05-16","cited_by_count":15,"area":"offlinerl"},{"id":"2303.02891","title":"Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback","created":"2023-03-06","cited_by_count":15,"area":"alignment"},{"id":"2308.04332","title":"RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback","created":"2023-08-08","cited_by_count":15,"area":"alignment"},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2407.19280","title":"Large Language Models for Human-like Autonomous Driving: A Survey","created":"2024-07-27","cited_by_count":14,"area":"driving"},{"id":"2101.07691","title":"Choice Set Misspecification in Reward Inference","created":"2021-01-19","cited_by_count":13,"area":"alignment"},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13,"area":"offlinerl"},{"id":"2205.15367","title":"Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning","created":"2022-05-30","cited_by_count":13,"area":"alignment"},{"id":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13,"area":"alignment"},{"id":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13,"area":"alignment"},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2402.03081","title":"Preference-Conditioned Language-Guided Abstraction","created":"2024-02-05","cited_by_count":12,"area":"offlinerl"},{"id":"2106.10394","title":"Uncertain Decisions Facilitate Better Preference Learning","created":"2021-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2412.19436","title":"Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedback","created":"2024-12-27","cited_by_count":10,"area":"alignment"},{"id":"2502.21038","title":"Reward Learning from Multiple Feedback Types","created":"2025-02-28","cited_by_count":9,"area":"agents"},{"id":"2602.21158","title":"SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards","created":"2026-02-24","cited_by_count":9,"area":"agents"},{"id":"2106.14866","title":"Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","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":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2111.04698","title":"Interactive Inverse Reinforcement Learning for Cooperative Games","created":"2021-11-08","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":"2407.18421","title":"Self-Directed Synthetic Dialogues and Revisions Technical Report","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2410.17233","title":"ICPL: Few-shot In-context Preference Learning via LLMs","created":"2024-10-22","cited_by_count":7,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"area":"alignment"},{"id":"2204.05091","title":"Linguistic communication as (inverse) reward design","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2212.03922","title":"Tight Performance Guarantees of Imitator Policies with Continuous Actions","created":"2022-12-07","cited_by_count":6,"area":"offlinerl"},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2204.07123","title":"Retrospective on the 2021 BASALT Competition on Learning from Human Feedback","created":"2022-04-14","cited_by_count":5,"area":"alignment"},{"id":"2212.09586","title":"Learning Latent Representations to Co-Adapt to Humans","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2406.03812","title":"How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach","created":"2024-06-06","cited_by_count":5,"area":"offlinerl"},{"id":"2411.11761","title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","created":"2024-11-18","cited_by_count":5,"area":"agents"},{"id":"2210.14972","title":"Environment Design for Inverse Reinforcement Learning","created":"2022-10-26","cited_by_count":4,"area":"offlinerl"},{"id":"2502.17721","title":"Aligning Compound AI Systems via System-level DPO","created":"2025-02-24","cited_by_count":4,"area":"alignment"},{"id":"2503.09173","title":"Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2307.03887","title":"Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining","created":"2023-07-08","cited_by_count":3,"area":"alignment"},{"id":"2312.04030","title":"Modeling Boundedly Rational Agents with Latent Inference Budgets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2105.11977","title":"Towards Teachable Autotelic Agents","created":"2021-05-25","cited_by_count":2,"area":null},{"id":"2305.04692","title":"Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks","created":"2023-05-08","cited_by_count":2,"area":null},{"id":"2305.12235","title":"Joining the Conversation: Towards Language Acquisition for Ad Hoc Team Play","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2505.00490","title":"Optimal Interactive Learning on the Job via Facility Location Planning","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2507.14063","title":"Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2512.09212","title":"Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment","created":"2025-12-10","cited_by_count":2,"area":"alignment"},{"id":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2211.15542","title":"Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning","created":"2022-11-28","cited_by_count":1,"area":"offlinerl"},{"id":"2302.00813","title":"Goal Alignment: A Human-Aware Account of Value Alignment Problem","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2302.09324","title":"Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2303.00822","title":"Planning for Attacker Entrapment in Adversarial Settings","created":"2023-03-01","cited_by_count":1,"area":null},{"id":"2401.02225","title":"Trajectory-Oriented Policy Optimization with Sparse Rewards","created":"2024-01-04","cited_by_count":1,"area":"deeprl"},{"id":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"id":"2507.00611","title":"Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics","created":"2025-07-01","cited_by_count":1,"area":"alignment"},{"id":"2508.14027","title":"Learning from Preferences and Mixed Demonstrations in General Settings","created":"2025-08-19","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}