{"total":39,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"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":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43,"area":"alignment"},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40,"area":"alignment"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"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":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"area":"alignment"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2505.12763","title":"Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization","created":"2025-05-19","cited_by_count":11,"area":"alignment"},{"id":"2402.08005","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","created":"2024-02-12","cited_by_count":10,"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":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2405.16681","title":"Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization","created":"2024-05-26","cited_by_count":6,"area":"alignment"},{"id":"2412.06827","title":"Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback","created":"2024-12-06","cited_by_count":6,"area":"alignment"},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2410.10392","title":"Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search","created":"2024-10-14","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","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":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2604.05502","title":"AttnDiff: Attention-based Differential Fingerprinting for Large Language Models","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2405.00578","title":"The Real, the Better: Aligning Large Language Models with Online Human Behaviors","created":"2024-05-01","cited_by_count":3,"area":"alignment"},{"id":"2406.11301","title":"Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants","created":"2024-06-17","cited_by_count":3,"area":"alignment"},{"id":"2510.15839","title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2601.08097","title":"AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling","created":"2026-01-13","cited_by_count":1,"area":"alignment"},{"id":"2601.22083","title":"Latent Adversarial Regularization for Offline Preference Optimization","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2603.18258","title":"Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization","created":"2026-03-18","cited_by_count":1,"area":"alignment"},{"id":"2505.12845","title":"Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks","created":"2025-05-19","cited_by_count":0,"area":"alignment"},{"id":"2604.25077","title":"Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.10981","title":"$\\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2610.07592","title":"LSC-DPO: Learning-Signal-Controlled Direct Preference Optimization","created":"2026-10-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}