Prediction-Powered Inference

Overview

Prediction-Powered Inference combines abundant model predictions or unlabeled data with a smaller set of trusted labels to estimate quantities while correcting for prediction errors. Common approaches include calibration, residual-based control variates, cross-fitting, active label sampling, and combining multiple predictors. These methods support estimates and tests for means, risks, causal effects, rankings, and other quantities, including in AI evaluation and dependent time-series settings. The central tension is that noisy predictions can improve precision, but gains depend on their relationship to true outcomes and methods must preserve valid uncertainty estimates under finite samples, model error, or domain shift.

Latest papers

CardsList

34 papers4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

  1. Prediction-Powered LLM Ranking with Adaptively Collected Human Feedback

    Nov 9, 2026Gabriel Sargent, Will Wei Sun, Zhengwu Zhang +1LLM EvaluationHuman-in-the-Loop Evaluation

  2. Crop Mapping Evaluation under Sampling Bias

    Oct 31, 2026Akram Zaytar, Kemunto Ochwang'i, Caleb Robinson +5Crop Type ClassificationPrediction-Powered Inference

  3. Bayes-Consistent Losses for Adaptive Inference in Classification

    Oct 29, 2026Shirley Xiaoqi Liu, Florence Regol, Antonios Valkanas +2Adaptive Model RoutingAdaptive Inference

  4. Conducting Reliable Keyword Estimation with Unreliable ASR in Police Audio Data

    Oct 19, 2026Robert Cole Molloy, Rhiannon N. Miller, Stephen Morgan +1Supervised LearningAutomatic Speech Recognition

  5. Prediction-Powered Data Fusion for Treatment Effect Estimation

    Oct 8, 2026Yonghan Jung, Shu YangCausal Effect EstimationConditional Average Treatment Effect Estimation

  6. Prediction-powered inference for time series across space

    Oct 6, 2026Shahzar Rizvi, David Burt, Vishwak Srinivasan +3Spatiotemporal ForecastingPrediction-Powered Inference

  7. Prediction-powered Neural Architecture Search

    Oct 1, 2026Pascal Janetzky, Yuxin Wang, Michael Klar +1Neural Architecture SearchPrediction-Powered Inference

  8. ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control

    Sep 28, 2026Eric Frankel, Banghua Zhu, Sewoong Oh +1RL for Language ModelsLLM Alignment

  9. Transfer Calibrated Prediction Powered Inference

    Sep 28, 2026Aditya T. Vadlamani, Jae Ho Chang, Srinivasan Parthasarathy +1Cross-FittingDomain Adaptation

  10. How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional Coverage

    Sep 27, 2026Qianyi Chen, Bo LiQuantile RegressionConformal Prediction

  11. Augmented Hypothesis Testing with Persona-Based LLM Simulations

    Sep 21, 2026Ziyad Benomar, Aymen Al Marjani, Paul Missault +1A/b TestingLearning-Augmented Algorithms

  12. How to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats

    Sep 20, 2026Ian ArawjoStatistical Hypothesis TestingLLM Evaluation

  13. Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

    Sep 17, 2026Sho Kawano, Zehang Richard Li, Paul A. ParkerAI Agent EvaluationPrediction-Powered Inference

  14. Calibrating Small Language Models for Claim Check-Worthiness Detection

    Aug 31, 2026Pratuat Amatya, V Venktesh, Vinay SettyClaim VerificationSmall Language Models

  15. Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation

    Aug 27, 2026Mingqi Gao, Anthony Sicilia, Weiyan ShiAutomated EvaluationMT Evaluation

  16. The Measurement Revolution? Credible Measurement and Inference in the Age of AI

    Aug 24, 2026Melissa Dell, Ashesh RambachanPrediction-Powered Inference

  17. Prediction-Powered Active Testing

    Jul 9, 2026Kianoosh Ashouritaklimi, Valentin Kilian, Daolang Huang +2Confidence Region EstimationVariance Reduction

  18. Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation

    May 29, 2026Grégoire Martinon, Ibrahim Merad, Mohammed RakiLLM-Assisted AnnotationLLM Agent Evaluation

  19. Active Multiple-Prediction-Powered Inference

    May 8, 2026Nicholas Brawand, Nima Leclerc, Anhthy Ngo +4Adaptive InferenceCost-Aware Inference

  20. Prediction-powered Inference by Mixture of Experts

    Apr 30, 2026Yanwu Gu, Linglong Kong, Dong XiaUncertainty QuantificationMixture-of-Experts Models

  21. Calibeating Prediction-Powered Inference

    Apr 23, 2026Lars van der Laan, Mark Van Der LaanInverse Probability WeightingParameter Estimation

  22. Revisiting Active Sequential Prediction-Powered Mean Estimation

    Apr 20, 2026Maria-Eleni Sfyraki, Jun-Kun WangParameter EstimationActive Learning

  23. Allocating Human Oversight in AI-Enabled Analytics

    Apr 14, 2026Zikun Ye, Jiameng Lyu, Rui TaoHuman Oversight of AIHuman-in-the-Loop Annotation

  24. Multiple-Prediction-Powered Inference

    Mar 28, 2026Charlie Cowen-Breen, Alekh Agarwal, Stephen Bates +4Prediction-Powered Inference

  25. Power Analysis for Prediction-Powered Inference

    Mar 17, 2026Yiqun T. Chen, Moran Guo, Shengy LiStatistical Power AnalysisPrediction-Powered Inference