{"total":36,"rows":[{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"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":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"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":"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":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"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":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"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":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"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":"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":"2405.18688","title":"Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation","created":"2024-05-29","cited_by_count":9,"area":"alignment"},{"id":"2502.00634","title":"SimulPL: Aligning Human Preferences in Simultaneous Machine Translation","created":"2025-02-02","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":"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":"2503.04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference","created":"2025-03-01","cited_by_count":5,"area":"alignment"},{"id":"2411.09341","title":"Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment","created":"2024-11-14","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":"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":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","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":"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":"2504.15472","title":"LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning","created":"2025-04-21","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":"2406.10445","title":"Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning","created":"2024-06-14","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":"2503.18347","title":"Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners","created":"2025-03-24","cited_by_count":1,"area":"alignment"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2412.21001","title":"LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency","created":"2024-12-30","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":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}