{"total":115,"rows":[{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"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":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"area":"alignment"},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"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":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"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":"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":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90,"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":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","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":"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":"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":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"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":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","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":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"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":"2504.04950","title":"A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization","created":"2025-04-07","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":"2410.16714","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","created":"2024-10-22","cited_by_count":20,"area":"alignment"},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","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":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2303.13512","title":"Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition","created":"2023-03-23","cited_by_count":15,"area":"alignment"},{"id":"2307.15801","title":"Primitive Skill-based Robot Learning from Human Evaluative Feedback","created":"2023-07-28","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14,"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":"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":"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":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","cited_by_count":12,"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":"2406.12168","title":"BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment","created":"2024-06-18","cited_by_count":9,"area":"alignment"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","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":"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":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2006.16498","title":"Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback","created":"2020-06-30","cited_by_count":4,"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":"2406.06874","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2407.13163","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","created":"2024-07-18","cited_by_count":4,"area":"alignment"},{"id":"2305.07036","title":"GFlowNets with Human Feedback","created":"2023-05-11","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":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","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":"2505.18407","title":"KL-regularization Itself is Differentially Private in Bandits and RLHF","created":"2025-05-23","cited_by_count":3,"area":"alignment"},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","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":"2510.18913","title":"ADPO: Anchored Direct Preference Optimization","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2511.02094","title":"Automated Reward Design for Gran Turismo","created":"2025-11-03","cited_by_count":3,"area":"alignment"},{"id":"2606.02521","title":"Drifting Preference Optimization for One-Step Generative Models","created":"2026-06-01","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":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2405.17618","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","created":"2024-05-27","cited_by_count":2,"area":"alignment"},{"id":"2410.20176","title":"Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning","created":"2024-10-26","cited_by_count":2,"area":"alignment"},{"id":"2502.12198","title":"Maximize Your Diffusion: A Study into Reward Maximization and Alignment for Diffusion-based Control","created":"2025-02-16","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":"2506.03519","title":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","created":"2025-06-04","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":"2302.11917","title":"Diverse Policy Optimization for Structured Action Space","created":"2023-02-23","cited_by_count":1,"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":"2403.19024","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","created":"2024-03-27","cited_by_count":1,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","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":"2411.00361","title":"Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach","created":"2024-11-01","cited_by_count":1,"area":"alignment"},{"id":"2503.00930","title":"Behavior Preference Regression for Offline Reinforcement Learning","created":"2025-03-02","cited_by_count":1,"area":"alignment"},{"id":"2505.19743","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2506.14648","title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","created":"2025-06-17","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":"2508.18741","title":"Stability and Generalization for Bellman Residuals","created":"2025-08-26","cited_by_count":1,"area":"alignment"},{"id":"2509.22807","title":"MTRec: Learning to Align with User Preferences via Mental Reward Models","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"area":"alignment"},{"id":"2411.00252","title":"IO Transformer: Evaluating SwinV2-Based Reward Models for Computer Vision","created":"2024-10-31","cited_by_count":0,"area":"alignment"},{"id":"2503.04679","title":"Multi-Agent Inverse Q-Learning from Demonstrations","created":"2025-03-06","cited_by_count":0,"area":"alignment"},{"id":"2508.11363","title":"Fusing Rewards and Preferences in Reinforcement Learning","created":"2025-08-15","cited_by_count":0,"area":"alignment"},{"id":"2508.13415","title":"MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection","created":"2025-08-19","cited_by_count":0,"area":"alignment"},{"id":"2509.16965","title":"Preference Distillation via Value based Reinforcement Learning","created":"2025-09-21","cited_by_count":0,"area":"alignment"},{"id":"2509.20265","title":"Failure Modes of Maximum Entropy RLHF","created":"2025-09-24","cited_by_count":0,"area":"alignment"},{"id":"2512.00050","title":"Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control","created":"2025-11-18","cited_by_count":0,"area":"alignment"},{"id":"2512.20974","title":"Meta-RL with Bayesian Linear Task Models","created":"2025-12-24","cited_by_count":0,"area":"alignment"},{"id":"2601.09236","title":"Reward Learning through Ranking Mean Squared Error","created":"2026-01-14","cited_by_count":0,"area":"alignment"},{"id":"2601.16906","title":"The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning","created":"2026-01-23","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}