{"total":61,"rows":[{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2306.00622","title":"ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing","created":"2023-06-01","cited_by_count":122,"area":null},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62,"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":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33,"area":"alignment"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2303.07152","title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","created":"2023-03-13","cited_by_count":21,"area":null},{"id":"2110.00151","title":"Lagrangian Inference for Ranking Problems","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2209.05742","title":"A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game","created":"2022-09-13","cited_by_count":16,"area":null},{"id":"2107.01854","title":"Poisoning Attack against Estimating from Pairwise Comparisons","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2502.17515","title":"Towards User-level Private Reinforcement Learning with Human Feedback","created":"2025-02-22","cited_by_count":14,"area":"alignment"},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"id":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12,"area":"alignment"},{"id":"2308.02918","title":"Spectral Ranking Inferences based on General Multiway Comparisons","created":"2023-08-05","cited_by_count":11,"area":null},{"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":"2110.10825","title":"$\\ell_{\\infty}$-Bounds of the MLE in the BTL Model under General Comparison Graphs","created":"2021-10-20","cited_by_count":9,"area":null},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2312.15081","title":"Learning Rich Rankings","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2405.02612","title":"Learning Linear Utility Functions From Pairwise Comparison Queries","created":"2024-05-04","cited_by_count":8,"area":null},{"id":"2211.12868","title":"Perfect Sampling from Pairwise Comparisons","created":"2022-11-23","cited_by_count":6,"area":null},{"id":"2304.06821","title":"Ranking from Pairwise Comparisons in General Graphs and Graphs with Locality","created":"2023-04-13","cited_by_count":6,"area":null},{"id":"2310.00260","title":"On Sinkhorn's Algorithm and Choice Modeling","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2406.16507","title":"Statistical ranking with dynamic covariates","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2206.09146","title":"A Perceptually Optimized and Self-Calibrated Tone Mapping Operator","created":"2022-06-18","cited_by_count":3,"area":null},{"id":"2309.04626","title":"Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2401.08463","title":"Statistical inference for pairwise comparison models","created":"2024-01-16","cited_by_count":3,"area":null},{"id":"2402.07445","title":"Top-$K$ ranking with a monotone adversary","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2402.18697","title":"Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2410.08360","title":"Minimax Hypothesis Testing for the Bradley-Terry-Luce Model","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2501.18282","title":"Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective","created":"2025-01-30","cited_by_count":3,"area":"alignment"},{"id":"2510.25240","title":"Generative Bayesian Optimization: Generative Models as Acquisition Functions","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2602.10286","title":"What Does Preference Learning Recover from Pairwise Comparison Data?","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2303.06234","title":"Optimal and Private Learning from Human Response Data","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","cited_by_count":2,"area":"alignment"},{"id":"2204.08880","title":"Antipatterns in Software Classification Taxonomies","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2402.14244","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","created":"2024-02-22","cited_by_count":1,"area":"alignment"},{"id":"2406.05869","title":"An Analysis of Elo Rating Systems via Markov Chains","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2502.20033","title":"Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2505.23557","title":"Learning Parametric Distributions from Samples and Preferences","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2507.09388","title":"Optimal Differentially Private Ranking from Pairwise Comparisons","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2512.02912","title":"Hypothesis Testing for Generalized Thurstone Models","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2605.23854","title":"Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2111.10021","title":"Achievability and Impossibility of Exact Pairwise Ranking","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2205.01607","title":"Modeling and Correcting Bias in Sequential Evaluation","created":"2022-05-03","cited_by_count":0,"area":null},{"id":"2209.08665","title":"Allocation Schemes in Analytic Evaluation: Applicant-Centric Holistic or Attribute-Centric Segmented?","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2307.13397","title":"Scoring Cycling Environments Perceived Safety using Pairwise Image Comparisons","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2406.13989","title":"Random pairing MLE for estimation of item parameters in Rasch model","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2501.07437","title":"Pairwise Comparisons without Stochastic Transitivity: Model, Theory and Applications","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2505.06601","title":"Learning Guarantee of Reward Modeling Using Deep Neural Networks","created":"2025-05-10","cited_by_count":0,"area":"alignment"},{"id":"2510.01871","title":"Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2512.21111","title":"Statistical and computational challenges in ranking","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2606.08410","title":"Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.03494","title":"Towards Standardized Light Field Quality Assessment: Hybrid Subjective Benchmarking and Objective Metric Evaluation","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.24732","title":"Learning Distributions from Multiple Data Providers","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.27967","title":"MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.07859","title":"Adaptive KappaSharp: Condition-Number Shaping for Preferential Bayesian Optimization","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2610.06237","title":"Bradley-Terry model under general comparison graphs","created":"2026-10-05","cited_by_count":0,"area":"alignment"},{"id":"2610.17956","title":"Learning Distributions from Samples and Qualities","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}