{"total":133,"rows":[{"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":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285,"area":"alignment"},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160,"area":"alignment"},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"area":"alignment"},{"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":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"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":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","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":"2603.02115","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","created":"2026-03-02","cited_by_count":60,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"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":"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":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"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":"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":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"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":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"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":"2406.04412","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment","created":"2024-06-06","cited_by_count":27,"area":"alignment"},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25,"area":"alignment"},{"id":"2301.11774","title":"Reinforcement Learning from Diverse Human Preferences","created":"2023-01-27","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":"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":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"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":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13,"area":"alignment"},{"id":"2307.11049","title":"Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback","created":"2023-07-20","cited_by_count":13,"area":"alignment"},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2406.07780","title":"A Critical Look At Tokenwise Reward-Guided Text Generation","created":"2024-06-12","cited_by_count":12,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2405.19806","title":"Preference Alignment with Flow Matching","created":"2024-05-30","cited_by_count":11,"area":"alignment"},{"id":"2306.03615","title":"PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation","created":"2023-06-06","cited_by_count":9,"area":"alignment"},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2405.18688","title":"Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation","created":"2024-05-29","cited_by_count":9,"area":"alignment"},{"id":"2210.09151","title":"Symbol Guided Hindsight Priors for Reward Learning from Human Preferences","created":"2022-10-17","cited_by_count":8,"area":"alignment"},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7,"area":"alignment"},{"id":"2307.10867","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","created":"2023-07-20","cited_by_count":7,"area":"alignment"},{"id":"2401.10941","title":"Crowd-PrefRL: Preference-Based Reward Learning from Crowds","created":"2024-01-17","cited_by_count":7,"area":"alignment"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2410.17233","title":"ICPL: Few-shot In-context Preference Learning via LLMs","created":"2024-10-22","cited_by_count":7,"area":"alignment"},{"id":"2410.17389","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","created":"2024-10-22","cited_by_count":7,"area":"alignment"},{"id":"2412.16878","title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","created":"2024-12-22","cited_by_count":7,"area":"alignment"},{"id":"2502.01616","title":"Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning","created":"2025-02-03","cited_by_count":7,"area":"alignment"},{"id":"2505.06079","title":"TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations","created":"2025-05-09","cited_by_count":7,"area":"alignment"},{"id":"2409.11212","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization","created":"2024-09-17","cited_by_count":6,"area":"alignment"},{"id":"2310.06648","title":"Diversity from Human Feedback","created":"2023-10-10","cited_by_count":5,"area":"alignment"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2502.04517","title":"Towards Cost-Effective Reward Guided Text Generation","created":"2025-02-06","cited_by_count":5,"area":"alignment"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2302.08738","title":"Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":4,"area":"alignment"},{"id":"2501.06416","title":"Influencing Humans to Conform to Preference Models for RLHF","created":"2025-01-11","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2302.08733","title":"Data Driven Reward Initialization for Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":3,"area":"alignment"},{"id":"2311.01990","title":"Conditions on Preference Relations that Guarantee the Existence of Optimal Policies","created":"2023-11-03","cited_by_count":3,"area":"alignment"},{"id":"2404.13423","title":"PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling","created":"2024-04-20","cited_by_count":3,"area":"alignment"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2412.09104","title":"In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning","created":"2024-12-12","cited_by_count":3,"area":"alignment"},{"id":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2507.13171","title":"Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback","created":"2025-07-17","cited_by_count":3,"area":"alignment"},{"id":"2509.23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"id":"2405.13026","title":"Leveraging Human Revisions for Improving Text-to-Layout Models","created":"2024-05-16","cited_by_count":2,"area":"alignment"},{"id":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2502.14400","title":"HPS: Hard Preference Sampling for Human Preference Alignment","created":"2025-02-20","cited_by_count":2,"area":"alignment"},{"id":"2504.20520","title":"PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations","created":"2025-04-29","cited_by_count":2,"area":"alignment"},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2506.12529","title":"Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning","created":"2025-06-14","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2601.01904","title":"Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning","created":"2026-01-05","cited_by_count":2,"area":"alignment"},{"id":"2603.04861","title":"Causally Robust Reward Learning from Reason-Augmented Preference Feedback","created":"2026-03-05","cited_by_count":2,"area":"alignment"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","cited_by_count":1,"area":"alignment"},{"id":"2402.03282","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","created":"2024-02-05","cited_by_count":1,"area":"alignment"},{"id":"2402.14244","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","created":"2024-02-22","cited_by_count":1,"area":"alignment"},{"id":"2406.10892","title":"DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning","created":"2024-06-16","cited_by_count":1,"area":"alignment"},{"id":"2406.16258","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2409.20016","title":"Dynamic Policy Fusion for User Alignment Without Re-Interaction","created":"2024-09-30","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}