{"total":91,"rows":[{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"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":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"area":"alignment"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"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":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"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":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45,"area":"alignment"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2503.17662","title":"Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning","created":"2025-03-22","cited_by_count":27,"area":null},{"id":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2505.23749","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","created":"2025-05-29","cited_by_count":22,"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":"2406.01660","title":"Self-Improving Robust Preference Optimization","created":"2024-06-03","cited_by_count":19,"area":"alignment"},{"id":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2412.09243","title":"SPRec: Self-Play to Debias LLM-based Recommendation","created":"2024-12-12","cited_by_count":18,"area":"synth"},{"id":"2501.19266","title":"Jackpot! Alignment as a Maximal Lottery","created":"2025-01-31","cited_by_count":17,"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":"2503.08942","title":"Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback","created":"2025-03-11","cited_by_count":16,"area":"alignment"},{"id":"2410.10370","title":"Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2412.15650","title":"Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution","created":"2024-12-20","cited_by_count":11,"area":"mllm"},{"id":"2503.19612","title":"RL-finetuning LLMs from on- and off-policy data with a single algorithm","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","cited_by_count":10,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2405.01511","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","created":"2024-05-02","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":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2405.11870","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","created":"2024-05-20","cited_by_count":8,"area":"alignment"},{"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":"2503.06810","title":"Mitigating Preference Hacking in Policy Optimization with Pessimism","created":"2025-03-10","cited_by_count":8,"area":"alignment"},{"id":"2512.20806","title":"Safety Alignment of LMs via Non-cooperative Games","created":"2025-12-23","cited_by_count":8,"area":"alignment"},{"id":"2404.04291","title":"Investigating Regularization of Self-Play Language Models","created":"2024-04-04","cited_by_count":7,"area":"alignment"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2406.17312","title":"Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning","created":"2024-06-25","cited_by_count":7,"area":null},{"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":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"area":"alignment"},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"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":"2602.03425","title":"ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning","created":"2026-02-03","cited_by_count":6,"area":"deeprl"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","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":"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":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2508.17850","title":"GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning","created":"2025-08-25","cited_by_count":4,"area":"deeprl"},{"id":"2502.01237","title":"The Differences Between Direct Alignment Algorithms are a Blur","created":"2025-02-03","cited_by_count":3,"area":"alignment"},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2511.00040","title":"Semi-Supervised Preference Optimization with Limited Feedback","created":"2025-10-28","cited_by_count":3,"area":"alignment"},{"id":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2507.02984","title":"From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought","created":"2025-07-01","cited_by_count":2,"area":"lr"},{"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":"2602.12180","title":"How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics","created":"2026-02-12","cited_by_count":2,"area":"alignment"},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2602.01357","title":"Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning","created":"2026-02-01","cited_by_count":1,"area":"synth"},{"id":"2504.05112","title":"ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog through Dynamic Frequency-Spatial Synergy","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2506.11098","title":"Debiasing Online Preference Learning via Preference Feature Preservation","created":"2025-06-06","cited_by_count":0,"area":"alignment"},{"id":"2512.24818","title":"Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback","created":"2025-12-31","cited_by_count":0,"area":"alignment"},{"id":"2601.08777","title":"Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","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":"2609.08082","title":"Inference-Time Nash Alignment","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.16340","title":"StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation","created":"2026-09-14","cited_by_count":0,"area":"alignment"},{"id":"2609.34528","title":"Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00715","title":"Robust Nash Alignment under Preference Uncertainty","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.14763","title":"CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation","created":"2026-10-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}