{"total":69,"rows":[{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"area":"alignment"},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2503.01067","title":"All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning","created":"2025-03-03","cited_by_count":59,"area":"alignment"},{"id":"2406.01462","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage","created":"2024-06-03","cited_by_count":55,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2505.17147","title":"MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming","created":"2025-05-22","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":"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":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"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":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2411.11727","title":"Aligning Few-Step Diffusion Models with Dense Reward Difference Learning","created":"2024-11-18","cited_by_count":12,"area":"diffusion"},{"id":"2410.18870","title":"End-to-end Training for Recommendation with Language-based User Profiles","created":"2024-10-24","cited_by_count":10,"area":null},{"id":"2410.20727","title":"Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment","created":"2024-10-28","cited_by_count":9,"area":"alignment"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2410.23223","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","created":"2024-10-30","cited_by_count":8,"area":"alignment"},{"id":"2502.12146","title":"Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening","created":"2025-02-17","cited_by_count":7,"area":"diffusion"},{"id":"2410.19230","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2412.10616","title":"Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration","created":"2024-12-13","cited_by_count":6,"area":"alignment"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2407.02119","title":"Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning","created":"2024-07-02","cited_by_count":5,"area":"alignment"},{"id":"2503.00030","title":"RSPO: Regularized Self-Play Alignment of Large Language Models","created":"2025-02-24","cited_by_count":5,"area":"alignment"},{"id":"2603.14128","title":"Diffusion Reinforcement Learning via Centered Reward Distillation","created":"2026-03-14","cited_by_count":5,"area":"diffusion"},{"id":"2606.14657","title":"HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities","created":"2026-06-12","cited_by_count":5,"area":"diffusion"},{"id":"2405.17956","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier","created":"2024-05-28","cited_by_count":4,"area":"alignment"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2506.01523","title":"Beyond RLHF: A Unified Theoretical Framework of Alignment","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2507.16679","title":"PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2509.24323","title":"MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems","created":"2025-09-29","cited_by_count":3,"area":"agents"},{"id":"2510.20413","title":"Why DPO is a Misspecified Estimator and How to Fix It","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2505.20107","title":"Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning","created":"2025-05-26","cited_by_count":2,"area":"diffusion"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2503.00930","title":"Behavior Preference Regression for Offline Reinforcement Learning","created":"2025-03-02","cited_by_count":1,"area":"alignment"},{"id":"2506.08681","title":"Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling","created":"2025-06-10","cited_by_count":1,"area":"alignment"},{"id":"2508.08486","title":"Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2601.16419","title":"Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning","created":"2026-01-23","cited_by_count":1,"area":"mllm"},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2507.22926","title":"Multi-Relation Extraction in Entity Pairs using Global Context","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2511.18581","title":"TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization","created":"2025-11-23","cited_by_count":0,"area":"safety"},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.07775","title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.29758","title":"PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2608.19748","title":"Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2610.04638","title":"Policy as Data: Replay-Based Policy Dual Averaging via Advantage Regression","created":"2026-10-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.13755","title":"Matched-Context Group Policy Optimization for LLM Agent Training","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}