{"total":72,"rows":[{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135,"area":"alignment"},{"id":"2406.00832","title":"BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling","created":"2024-06-02","cited_by_count":121,"area":"alignment"},{"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":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"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":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25,"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":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2409.12403","title":"Preference Alignment Improves Language Model-Based TTS","created":"2024-09-19","cited_by_count":21,"area":"alignment"},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2410.16027","title":"ComPO: Community Preferences for Language Model Personalization","created":"2024-10-21","cited_by_count":19,"area":"alignment"},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17,"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":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","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":"2505.23349","title":"Towards Reward Fairness in RLHF: From a Resource Allocation Perspective","created":"2025-05-29","cited_by_count":9,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2405.14769","title":"Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input","created":"2024-05-23","cited_by_count":8,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2504.02882","title":"DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models","created":"2025-04-02","cited_by_count":8,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","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":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2410.09181","title":"Can a large language model be a gaslighter?","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2510.02850","title":"Reward Model Routing in Alignment","created":"2025-10-03","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":"2502.04774","title":"SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation","created":"2025-02-07","cited_by_count":3,"area":"alignment"},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","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":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2503.12301","title":"One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","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":"2505.22820","title":"Preference Learning with Response Time: Robust Losses and Guarantees","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2506.05748","title":"Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2509.25562","title":"IRIS: Intrinsic Reward Image Synthesis","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2512.13837","title":"Explainable reinforcement learning from human feedback to improve alignment","created":"2025-12-15","cited_by_count":1,"area":"alignment"},{"id":"2603.20453","title":"Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2607.08647","title":"Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning","created":"2026-07-09","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":"2505.19134","title":"Incentivizing High-Quality Human Annotations with Golden Questions","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2507.12041","title":"Granular feedback merits sophisticated aggregation","created":"2025-07-16","cited_by_count":0,"area":"alignment"},{"id":"2510.13830","title":"Users as Annotators: LLM Preference Learning from Comparison Mode","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2606.18747","title":"Generating Natural and Expressive Robot Gestures through Iterative Reinforcement Learning with Human Feedback using LLMs","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2607.09796","title":"Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels","created":"2026-07-09","cited_by_count":0,"area":"alignment"},{"id":"2609.05111","title":"Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.17847","title":"Learning Heterogeneous Preferences","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2610.02844","title":"DNAlign: Dynamic Null-Space Safe Alignment for LLMs","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.20350","title":"Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}