{"list":"other","total":81,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2301.09633","title":"Prediction-Powered Inference","created":"2023-01-23","cited_by_count":220},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214},{"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},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150},{"id":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125},{"id":"2311.01453","title":"PPI++: Efficient Prediction-Powered Inference","created":"2023-11-02","cited_by_count":117},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"2410.14872","title":"How to Evaluate Reward Models for RLHF","created":"2024-10-18","cited_by_count":88},{"id":"2008.00051","title":"On the Convergence of SGD with Biased Gradients","created":"2020-07-31","cited_by_count":83},{"id":"2202.07136","title":"Debiased Self-Training for Semi-Supervised Learning","created":"2022-02-15","cited_by_count":62},{"id":"2309.16598","title":"Cross-Prediction-Powered Inference","created":"2023-09-28","cited_by_count":58},{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51},{"id":"2403.03208","title":"Active Statistical Inference","created":"2024-03-05","cited_by_count":50},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41},{"id":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40},{"id":"2011.01868","title":"Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance","created":"2020-11-03","cited_by_count":35},{"id":"2501.09731","title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","created":"2025-01-16","cited_by_count":34},{"id":"2401.12086","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","created":"2024-01-22","cited_by_count":28},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21},{"id":"2501.18577","title":"Prediction-Powered Inference with Imputed Covariates and Nonuniform Sampling","created":"2025-01-30","cited_by_count":19},{"id":"2306.00265","title":"Doubly Robust Self-Training","created":"2023-06-01","cited_by_count":18},{"id":"2511.03710","title":"Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards","created":"2025-11-05","cited_by_count":16},{"id":"2405.16236","title":"A transfer learning framework for weak-to-strong generalization","created":"2024-05-25","cited_by_count":14},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13},{"id":"1906.01133","title":"On Biased Stochastic Gradient Estimation","created":"2019-06-04","cited_by_count":11},{"id":"2401.03893","title":"Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation","created":"2024-01-08","cited_by_count":10},{"id":"2405.18379","title":"A Note on the Prediction-Powered Bootstrap","created":"2024-05-28","cited_by_count":10},{"id":"2601.20819","title":"Demystifying Prediction Powered Inference","created":"2026-01-28","cited_by_count":9},{"id":"2409.06903","title":"Semi-Supervised Reward Modeling via Iterative Self-Training","created":"2024-09-10","cited_by_count":8},{"id":"2505.20178","title":"No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference","created":"2025-05-26","cited_by_count":8},{"id":"2401.12764","title":"Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity","created":"2024-01-23","cited_by_count":7},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7},{"id":"2505.00282","title":"A Unifying Framework for Robust and Efficient Inference with Unstructured Data","created":"2025-05-01","cited_by_count":7},{"id":"2508.15162","title":"A Unified Framework for Inference with General Missingness Patterns and Machine Learning Imputation","created":"2025-08-21","cited_by_count":7},{"id":"2402.02857","title":"Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation","created":"2024-02-05","cited_by_count":5},{"id":"2410.13067","title":"Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way","created":"2024-10-16","cited_by_count":5},{"id":"2510.22586","title":"Prediction-Powered Semi-Supervised Learning with Online Power Tuning","created":"2025-10-26","cited_by_count":5},{"id":"2601.21470","title":"PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization","created":"2026-01-29","cited_by_count":4},{"id":"2602.16933","title":"M-estimation under Two-Phase Multiwave Sampling with Applications to Prediction-Powered Inference","created":"2026-02-18","cited_by_count":4},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4},{"id":"2604.21260","title":"Calibeating Prediction-Powered Inference","created":"2026-04-23","cited_by_count":4},{"id":"2512.21826","title":"Surrogate-Powered Inference: Regularization and Adaptivity","created":"2025-12-26","cited_by_count":3},{"id":"2605.29249","title":"Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research","created":"2026-05-28","cited_by_count":3}],"next_cursor":null}