{"total":95,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"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":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"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":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135,"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":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"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":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57,"area":"alignment"},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49,"area":"alignment"},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"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":"2504.19599","title":"GVPO: Group Variance Policy Optimization for Large Language Model Post-Training","created":"2025-04-28","cited_by_count":32,"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":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2407.14503","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","created":"2024-07-19","cited_by_count":23,"area":"alignment"},{"id":"2211.06519","title":"The Expertise Problem: Learning from Specialized Feedback","created":"2022-11-12","cited_by_count":20,"area":"alignment"},{"id":"2309.09055","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","created":"2023-09-16","cited_by_count":20,"area":"alignment"},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2511.16955","title":"Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models","created":"2025-11-21","cited_by_count":16,"area":"alignment"},{"id":"2402.14688","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","created":"2024-02-22","cited_by_count":15,"area":"alignment"},{"id":"2410.02743","title":"MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions","created":"2024-10-03","cited_by_count":15,"area":"alignment"},{"id":"2508.18312","title":"What Matters in Data for DPO?","created":"2025-08-23","cited_by_count":12,"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":"2412.04628","title":"Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts","created":"2024-12-05","cited_by_count":9,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","cited_by_count":8,"area":"alignment"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","created":"2025-04-16","cited_by_count":7,"area":"alignment"},{"id":"2508.04149","title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","created":"2025-08-06","cited_by_count":7,"area":"alignment"},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5,"area":"alignment"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2502.18293","title":"AMPO: Active Multi-Preference Optimization for Self-play Preference Selection","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2511.18039","title":"Curvature-Aware Safety Restoration In LLMs Fine-Tuning","created":"2025-11-22","cited_by_count":5,"area":"alignment"},{"id":"2602.03876","title":"GOPO: Policy Optimization using Ranked Rewards","created":"2026-02-01","cited_by_count":5,"area":"alignment"},{"id":"2403.08694","title":"TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning","created":"2024-03-13","cited_by_count":4,"area":"alignment"},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4,"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":"2505.18407","title":"KL-regularization Itself is Differentially Private in Bandits and RLHF","created":"2025-05-23","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":"2602.08813","title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2605.14366","title":"Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax","created":"2026-05-14","cited_by_count":3,"area":"alignment"},{"id":"2606.16771","title":"GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization","created":"2026-06-15","cited_by_count":3,"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":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2505.20359","title":"Risk-aware Direct Preference Optimization under Nested Risk Measure","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2511.03939","title":"RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods","created":"2025-11-06","cited_by_count":2,"area":"alignment"},{"id":"2512.22953","title":"APO: Alpha-Divergence Preference Optimization","created":"2025-12-28","cited_by_count":2,"area":"alignment"},{"id":"2604.05965","title":"Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment","created":"2026-04-07","cited_by_count":2,"area":"alignment"},{"id":"2607.04728","title":"Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment","created":"2026-07-06","cited_by_count":2,"area":"alignment"},{"id":"2407.13221","title":"Multimodal Label Relevance Ranking via Reinforcement Learning","created":"2024-07-18","cited_by_count":1,"area":"alignment"},{"id":"2506.13702","title":"Value-Free Policy Optimization via Reward Partitioning","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2506.17828","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","created":"2025-06-21","cited_by_count":1,"area":"alignment"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2602.11902","title":"Mitigating Mismatch within Reference-based Preference Optimization","created":"2026-02-12","cited_by_count":1,"area":"alignment"},{"id":"2602.20457","title":"Oracle-Robust Online Alignment for Large Language Models","created":"2026-02-24","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":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","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":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2506.01692","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","created":"2025-06-02","cited_by_count":0,"area":"alignment"},{"id":"2507.03069","title":"ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization","created":"2025-07-03","cited_by_count":0,"area":"alignment"},{"id":"2507.15906","title":"Towards Reliable, Uncertainty-Aware Alignment","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","cited_by_count":0,"area":"alignment"},{"id":"2512.24263","title":"Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2601.11574","title":"GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2602.17658","title":"MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling","created":"2026-02-19","cited_by_count":0,"area":"alignment"},{"id":"2602.21765","title":"Generalisation of RLHF under Reward Shift and Clipped KL Regularisation","created":"2026-02-25","cited_by_count":0,"area":"alignment"},{"id":"2603.04822","title":"VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2603.04974","title":"VRM: Teaching Reward Models to Understand Authentic Human Preferences","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2604.14895","title":"Beyond Importance Sampling: Rejection-Gated Policy Optimization","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2605.02320","title":"ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields","created":"2026-05-04","cited_by_count":0,"area":"alignment"},{"id":"2605.28030","title":"SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.24622","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2606.30339","title":"REAR: Test-time Preference Realignment through Reward Decomposition","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2607.07693","title":"Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2607.23153","title":"In-Context Learning as Implicit Policy Gradient","created":"2026-07-25","cited_by_count":0,"area":"alignment"},{"id":"2608.05040","title":"Private Direct Preference Optimization for LLM Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"}],"next_cursor":null}