{"total":316,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"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":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448,"area":"diffusion"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302,"area":"alignment"},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207,"area":null},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189,"area":"alignment"},{"id":"2303.09618","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","created":"2023-03-16","cited_by_count":173,"area":"alignment"},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160,"area":"alignment"},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142,"area":"offlinerl"},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108,"area":"offlinerl"},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2104.13906","title":"Reward (Mis)design for Autonomous Driving","created":"2021-04-28","cited_by_count":104,"area":"driving"},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"area":"alignment"},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96,"area":"offlinerl"},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88,"area":null},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"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":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"area":"alignment"},{"id":"2310.04799","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","created":"2023-10-07","cited_by_count":54,"area":"alignment"},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51,"area":"offlinerl"},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"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":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49,"area":"driving"},{"id":"2405.20495","title":"Transfer Q Star: Principled Decoding for LLM Alignment","created":"2024-05-30","cited_by_count":48,"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":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2310.10477","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","created":"2023-10-16","cited_by_count":35,"area":"alignment"},{"id":"2401.03160","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","created":"2024-01-06","cited_by_count":32,"area":"driving"},{"id":"2412.07775","title":"Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets","created":"2024-12-10","cited_by_count":32,"area":"diffusion"},{"id":"2110.06831","title":"Safe Driving via Expert Guided Policy Optimization","created":"2021-10-13","cited_by_count":31,"area":"driving"},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30,"area":"alignment"},{"id":"2406.00633","title":"Improving GFlowNets for Text-to-Image Diffusion Alignment","created":"2024-06-02","cited_by_count":27,"area":"diffusion"},{"id":"2410.02197","title":"Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment","created":"2024-10-03","cited_by_count":27,"area":"alignment"},{"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":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"id":"2301.11774","title":"Reinforcement Learning from Diverse Human Preferences","created":"2023-01-27","cited_by_count":24,"area":"alignment"},{"id":"2305.17608","title":"Reward Collapse in Aligning Large Language Models","created":"2023-05-28","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2311.14115","title":"A density estimation perspective on learning from pairwise human preferences","created":"2023-11-23","cited_by_count":23,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2109.12516","title":"Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving","created":"2021-09-26","cited_by_count":22,"area":"driving"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"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":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"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":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2310.02456","title":"Learning Optimal Advantage from Preferences and Mistaking it for Reward","created":"2023-10-03","cited_by_count":19,"area":"alignment"},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"}],"next_cursor":"100"}