{"total":57,"rows":[{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"area":"synth"},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"area":"alignment"},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122,"area":"lr"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2405.18641","title":"Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-05-28","cited_by_count":92,"area":"alignment"},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","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":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2311.00168","title":"The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback","created":"2023-10-31","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":"2404.14723","title":"Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks","created":"2024-04-23","cited_by_count":35,"area":"alignment"},{"id":"2405.13001","title":"Large Language Models for Education: A Survey","created":"2024-05-12","cited_by_count":34,"area":null},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30,"area":"alignment"},{"id":"2404.00934","title":"ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23,"area":"alignment"},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"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":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"area":"alignment"},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2505.13778","title":"CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs","created":"2025-05-19","cited_by_count":14,"area":"lr"},{"id":"2406.19185","title":"Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion","created":"2024-06-27","cited_by_count":13,"area":"alignment"},{"id":"2505.18531","title":"Generative RLHF-V: Learning Principles from Multi-modal Human Preference","created":"2025-05-24","cited_by_count":13,"area":"mllm"},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12,"area":"alignment"},{"id":"2412.18407","title":"A Statistical Framework for Ranking LLM-Based Chatbots","created":"2024-12-24","cited_by_count":12,"area":null},{"id":"2411.17792","title":"H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs","created":"2024-11-26","cited_by_count":11,"area":"alignment"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2506.15068","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation","created":"2025-06-18","cited_by_count":11,"area":"alignment"},{"id":"2510.06870","title":"$\\lambda$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2402.14228","title":"COPR: Continual Human Preference Learning via Optimal Policy Regularization","created":"2024-02-22","cited_by_count":9,"area":"alignment"},{"id":"2509.08486","title":"Too Helpful, Too Harmless, Too Honest or Just Right?","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2502.16944","title":"Pretrain Value, Not Reward: Decoupled Value Policy Optimization","created":"2025-02-24","cited_by_count":6,"area":"lr"},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2411.02442","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","created":"2024-11-02","cited_by_count":5,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2604.19857","title":"Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.10321","title":"Baseline-Free Policy Optimization for Neural Combinatorial Optimization","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2405.14103","title":"Online Self-Preferring Language Models","created":"2024-05-23","cited_by_count":0,"area":"alignment"},{"id":"2510.04096","title":"RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback","created":"2025-10-05","cited_by_count":0,"area":"agents"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2605.18191","title":"Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation","created":"2026-05-18","cited_by_count":0,"area":"alignment"},{"id":"2606.10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","created":"2026-06-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}