{"total":117,"rows":[{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57,"area":"synth"},{"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,"area":null},{"id":"2403.03208","title":"Active Statistical Inference","created":"2024-03-05","cited_by_count":50,"area":null},{"id":"2501.09731","title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","created":"2025-01-16","cited_by_count":34,"area":null},{"id":"2511.21140","title":"How to Correctly Report LLM-as-a-Judge Evaluations","created":"2025-11-26","cited_by_count":30,"area":null},{"id":"2402.17826","title":"Prediction-Powered Ranking of Large Language Models","created":"2024-02-27","cited_by_count":29,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2311.14220","title":"Assumption-Lean and Data-Adaptive Post-Prediction Inference","created":"2023-11-23","cited_by_count":26,"area":null},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2502.04294","title":"Prediction-Powered E-Values","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2312.06478","title":"Prediction De-Correlated Inference: A safe approach for post-prediction inference","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2506.16658","title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","created":"2025-06-20","cited_by_count":14,"area":null},{"id":"2510.04354","title":"Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators","created":"2025-10-05","cited_by_count":14,"area":"offlinerl"},{"id":"2412.11174","title":"Semi-Supervised Risk Control via Prediction-Powered Inference","created":"2024-12-15","cited_by_count":13,"area":null},{"id":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2405.18379","title":"A Note on the Prediction-Powered Bootstrap","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2405.20039","title":"Task-Agnostic Machine-Learning-Assisted Inference","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2502.04262","title":"Efficient Randomized Experiments Using Foundation Models","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2502.06343","title":"Prediction-Powered Causal Inferences","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2601.20819","title":"Demystifying Prediction Powered Inference","created":"2026-01-28","cited_by_count":9,"area":null},{"id":"2603.27414","title":"Multiple-Prediction-Powered Inference","created":"2026-03-28","cited_by_count":9,"area":null},{"id":"2409.18321","title":"Local Prediction-Powered Inference","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2502.19231","title":"AI-Powered Bayesian Inference","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2505.20178","title":"No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2411.12665","title":"Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2411.19908","title":"Another look at statistical inference with machine learning-imputed data","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2502.02363","title":"FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7,"area":"alignment"},{"id":"2505.18000","title":"Anytime-valid, Bayes-assisted, Prediction-Powered Inference","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2508.06635","title":"Valid Inference with Imperfect Synthetic Data","created":"2025-08-08","cited_by_count":7,"area":"synth"},{"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,"area":null},{"id":"2601.05420","title":"Efficient Inference for Noisy LLM-as-a-Judge Evaluation","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2603.19160","title":"PPI is the Difference Estimator: Recognizing the Survey Sampling Roots of Prediction-Powered Inference","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2412.11511","title":"Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2509.20345","title":"General Synthetic-Powered Inference","created":"2025-09-24","cited_by_count":6,"area":null},{"id":"2511.08991","title":"Robust Sampling for Active Statistical Inference","created":"2025-11-12","cited_by_count":6,"area":null},{"id":"2505.07367","title":"Generalization Bounds and Stopping Rules for Learning with Self-Selected Data","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2510.22586","title":"Prediction-Powered Semi-Supervised Learning with Online Power Tuning","created":"2025-10-26","cited_by_count":5,"area":null},{"id":"2505.18493","title":"Statistical Inference under Performativity","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2510.09801","title":"How can we assess human-agent interactions? Case studies in software agent design","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2511.09833","title":"ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking","created":"2025-11-13","cited_by_count":4,"area":"lr"},{"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,"area":null},{"id":"2602.08259","title":"A Statistical Framework for Alignment with Biased AI Feedback","created":"2026-02-09","cited_by_count":4,"area":"alignment"},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2604.21260","title":"Calibeating Prediction-Powered Inference","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2406.15819","title":"Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2508.10149","title":"Prediction-Powered Inference with Inverse Probability Weighting","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2512.05456","title":"Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2602.02229","title":"Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.10332","title":"Generalized Prediction-Powered Inference, with Application to Binary Classifier Evaluation","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.11368","title":"Spatially Robust Inference with Predicted and Missing at Random Labels","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2605.29249","title":"Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2607.05046","title":"CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion","created":"2026-07-06","cited_by_count":3,"area":null},{"id":"2401.08702","title":"Do We Really Even Need Data?","created":"2024-01-14","cited_by_count":2,"area":null},{"id":"2412.12365","title":"On the Role of Surrogates in Conformal Inference of Individual Causal Effects","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.15577","title":"Context-Aware Doubly-Robust Semi-Supervised Learning","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2509.04112","title":"Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2510.16166","title":"Extending Prediction-Powered Inference through Conformal Prediction","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2512.05267","title":"Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2601.22336","title":"Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.14575","title":"Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidence","created":"2026-04-16","cited_by_count":2,"area":"synth"},{"id":"2604.27892","title":"Prediction-powered Inference by Mixture of Experts","created":"2026-04-30","cited_by_count":2,"area":"moe"},{"id":"2606.25601","title":"Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2609.17560","title":"Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2505.21147","title":"Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.21753","title":"Towards a rigorous evaluation of RAG systems: the challenge of due diligence","created":"2025-07-29","cited_by_count":1,"area":"rag"},{"id":"2509.21707","title":"SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2604.05446","title":"MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.19296","title":"Debiased neural operators for estimating functionals","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.08429","title":"Active Multiple-Prediction-Powered Inference","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.28533","title":"Semi-Supervised Hypothesis Testing by Betting on Predictions","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.31278","title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.03211","title":"Optimized Labeling Resource Allocation for Prediction-Assisted Inference via OPAL","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.13629","title":"Valid Inference with Synthetic Data via Task Exchangeability","created":"2026-06-11","cited_by_count":1,"area":"synth"},{"id":"2606.14506","title":"Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.08347","title":"Prediction-Powered Active Testing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.07987","title":"When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.13148","title":"When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2509.22446","title":"Rescuing double robustness: safe estimation under complete misspecification","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.16937","title":"Prediction-Augmented Trees for Reliable Statistical Inference","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2601.01432","title":"Personalizing black-box models for nonparametric regression with minimax optimality","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.03791","title":"Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.04457","title":"Journey to the Centre of Cluster: Harnessing Interior Nodes for A/B Testing under Network Interference","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.03257","title":"Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.17267","title":"Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.23770","title":"Bootstrapping with AI/ML-generated labels","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.08069","title":"Empirical Bayes Rebiasing","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.11638","title":"Learning U-Statistics with Active Inference","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.05052","title":"Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.16239","title":"BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.17581","title":"Scalable Model-Assisted Multi-Target Estimation in Large Image Collections","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.10155","title":"Optimal Inference with Black-box Predictions","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":"100"}