{"list":"other","total":86,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"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":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"1510.04342","title":"Estimation and Inference of Heterogeneous Treatment Effects using Random Forests","created":"2015-10-14","cited_by_count":600},{"id":"1706.03461","title":"Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning","created":"2017-06-12","cited_by_count":478},{"id":"1712.04912","title":"Quasi-Oracle Estimation of Heterogeneous Treatment Effects","created":"2017-12-13","cited_by_count":332},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1906.02120","title":"Adapting Neural Networks for the Estimation of Treatment Effects","created":"2019-06-05","cited_by_count":287},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2504.05118","title":"VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks","created":"2025-04-07","cited_by_count":285},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"1907.09623","title":"Doubly robust off-policy evaluation with shrinkage","created":"2019-07-22","cited_by_count":87},{"id":"2410.15115","title":"On Designing Effective RL Reward at Training Time for LLM Reasoning","created":"2024-10-19","cited_by_count":87},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78},{"id":"1909.05850","title":"Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning","created":"2019-09-12","cited_by_count":75},{"id":"2007.11771","title":"Batch Policy Learning in Average Reward Markov Decision Processes","created":"2020-07-23","cited_by_count":69},{"id":"1507.00747","title":"Nonparametric methods for doubly robust estimation of continuous treatment effects","created":"2015-07-02","cited_by_count":64},{"id":"2011.08411","title":"Semiparametric proximal causal inference","created":"2020-11-17","cited_by_count":59},{"id":"1802.06037","title":"Policy Evaluation and Optimization with Continuous Treatments","created":"2018-02-16","cited_by_count":58},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52},{"id":"1806.03467","title":"Orthogonal Random Forest for Causal Inference","created":"2018-06-09","cited_by_count":51},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45},{"id":"2012.05862","title":"Understanding Learned Reward Functions","created":"2020-12-10","cited_by_count":37},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2403.05006","title":"Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback","created":"2024-03-08","cited_by_count":32},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"2001.09887","title":"Estimating heterogeneous treatment effects with right-censored data via causal survival forests","created":"2020-01-27","cited_by_count":29},{"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},{"id":"2002.11642","title":"Off-Policy Evaluation and Learning for External Validity under a Covariate Shift","created":"2020-02-26","cited_by_count":26},{"id":"2002.04014","title":"Statistically Efficient Off-Policy Policy Gradients","created":"2020-02-10","cited_by_count":25},{"id":"2205.04701","title":"StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random","created":"2022-05-10","cited_by_count":24},{"id":"1611.09925","title":"Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variables","created":"2016-11-29","cited_by_count":23},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","cited_by_count":23},{"id":"2006.02615","title":"Double Generative Adversarial Networks for Conditional Independence Testing","created":"2020-06-03","cited_by_count":22},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20},{"id":"2410.02504","title":"Dual Active Learning for Reinforcement Learning from Human Feedback","created":"2024-10-03","cited_by_count":20},{"id":"2410.06554","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","created":"2024-10-09","cited_by_count":19},{"id":"1912.06292","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","created":"2019-12-13","cited_by_count":17},{"id":"2010.15963","title":"Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings","created":"2020-10-29","cited_by_count":14},{"id":"2309.12600","title":"Multiply Robust Federated Estimation of Targeted Average Treatment Effects","created":"2023-09-22","cited_by_count":13},{"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":"2306.07024","title":"DRCFS: Doubly Robust Causal Feature Selection","created":"2023-06-12","cited_by_count":12},{"id":"2011.08661","title":"Debiased Inverse Propensity Score Weighting for Estimation of Average Treatment Effects with High-Dimensional Confounders","created":"2020-11-17","cited_by_count":11},{"id":"2311.02532","title":"Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making","created":"2023-11-05","cited_by_count":11},{"id":"2011.07234","title":"Improving efficiency of inference in clinical trials with external control data","created":"2020-11-14","cited_by_count":10},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10},{"id":"1407.7820","title":"On Estimation of Optimal Treatment Regimes For Maximizing t-Year Survival Probability","created":"2014-07-29","cited_by_count":9},{"id":"2412.13862","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model","created":"2024-12-18","cited_by_count":9},{"id":"2402.14979","title":"Optimizing Language Models for Human Preferences is a Causal Inference Problem","created":"2024-02-22","cited_by_count":8},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7},{"id":"2407.17694","title":"Doubly Robust Conditional Independence Testing with Generative Neural Networks","created":"2024-07-25","cited_by_count":7},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6},{"id":"2212.14466","title":"Quantile Off-Policy Evaluation via Deep Conditional Generative Learning","created":"2022-12-29","cited_by_count":5},{"id":"2505.20130","title":"Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach","created":"2025-05-26","cited_by_count":5},{"id":"2106.01474","title":"Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learning","created":"2021-06-02","cited_by_count":4},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4}],"next_cursor":null}