mlsanityData to 7 Oct 2026

Prediction-Powered Inference

arXiv 2301.09633 ↗First posted 23 Jan 2023stat.ML cs.AI cs.LGcited by 214

Not on the map. Why?

Abstract (arXiv)

Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms for computing provably valid confidence intervals for quantities such as means, quantiles, and linear and logistic regression coefficients, without making any assumptions on the machine-learning algorithm that supplies the predictions. Furthermore, more accurate predictions translate to smaller confidence intervals. Prediction-powered inference could enable researchers to draw valid and more data-efficient conclusions using machine learning. The benefits of prediction-powered inference are demonstrated with datasets from proteomics, astronomy, genomics, remote sensing, census analysis, and ecology.

Key facts. Cited by 214 papers in the map (data through 7 Oct 2026). Builds on 16 of its 74 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

16 of 74 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  5. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  6. 2020Estimating means of bounded random variables by bettingcited by 164
  7. 2021Transfer Learning under High-dimensional Generalized Linear Modelscited by 69
  8. 2016Semi-supervised Inference: General Theory and Estimation of Meanscited by 38
  9. 2020On the role of surrogates in the efficient estimation of treatment effects with limited outcome datacited by 36
  10. 2017Efficient and Adaptive Linear Regression in Semi-Supervised Settingscited by 29
  11. 2015WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classificationcited by 17
  12. 2020Optimal and Safe Estimation for High-Dimensional Semi-Supervised Learningcited by 10
4 more
  1. 2019High-dimensional semi-supervised learning: in search for optimal inference of the meancited by 8
  2. 2022A General Framework for Treatment Effect Estimation in Semi-Supervised and High Dimensional Settingscited by 8
  3. 2022Semi-Supervised Quantile Estimation: Robust and Efficient Inference in High Dimensional Settingscited by 8
  4. 2021Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Predictioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 29; 2025: 74; 2026: 99.

214 papers.

Sort:

By area:

  1. 2023PPI++: Efficient Prediction-Powered Inferencecited by 103
  2. 2025The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMscited by 72
  3. 2023Cross-Prediction-Powered Inferencecited by 57
  4. 2024AutoEval Done Right: Using Synthetic Data for Model Evaluationcited by 53
  5. 2024Active Statistical Inferencecited by 46
  6. 2024Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the datacited by 46
  7. 2023Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Modelscited by 37
  8. 2025Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AIcited by 31
  9. 2024Prediction-Powered Ranking of Large Language Modelscited by 29
  10. 2025How Benchmark Prediction from Fewer Data Misses the Markcited by 26
  11. 2026This human study did not involve human subjects: Validating LLM simulations as behavioral evidencecited by 26
  12. 2023Assumption-Lean and Data-Adaptive Post-Prediction Inferencecited by 25
38 more
  1. 2025How to Correctly Report LLM-as-a-Judge Evaluationscited by 25
  2. 2024Stratified Prediction-Powered Inference for Hybrid Language Model Evaluationcited by 24
  3. 2026Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judgescited by 23
  4. 2023Doubly Robust Self-Trainingcited by 18
  5. 2023Equal Opportunity of Coverage in Fair Regressioncited by 16
  6. 2025Prediction-Powered E-Valuescited by 16
  7. 2025Don't Pass@k: A Bayesian Framework for Large Language Model Evaluationcited by 15
  8. 2023Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithmscited by 14
  9. 2024Prediction-powered Generalization of Causal Inferencescited by 14
  10. 2024Active, anytime-valid risk controlling prediction setscited by 14
  11. 2025Cost-Optimal Active AI Model Evaluationcited by 14
  12. 2023Prediction De-Correlated Inference: A safe approach for post-prediction inferencecited by 13
  13. 2024A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimationcited by 13
  14. 2024Semi-Supervised Risk Control via Prediction-Powered Inferencecited by 13
  15. 2025Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuningcited by 13
  16. 2025Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewardscited by 13
  17. 2025Reliable and Scalable Robot Policy Evaluation with Imperfect Simulatorscited by 13
  18. 2024Smoke and Mirrors in Causal Downstream Taskscited by 12
  19. 2025Error-quantified Conformal Inference for Time Seriescited by 11
  20. 2024A Note on the Prediction-Powered Bootstrapcited by 10
  21. 2025Efficient Randomized Experiments Using Foundation Modelscited by 10
  22. 2025TabPFN: One Model to Rule Them All?cited by 10
  23. 2025Prediction-Powered Causal Inferencescited by 9
  24. 2025GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methodscited by 9
  25. 2025Synthetic-Powered Predictive Inferencecited by 9
  26. 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guaranteescited by 9
  27. 2025On Continuous Monitoring of Risk Violations under Unknown Shiftcited by 9
  28. 2026Multiple-Prediction-Powered Inferencecited by 9
  29. 2024Bayesian Prediction-Powered Inferencecited by 8
  30. 2024Task-Agnostic Machine-Learning-Assisted Inferencecited by 8
  31. 2025No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inferencecited by 8
  32. 2023Human-in-the-Loop Visual Re-ID for Population Size Estimationcited by 7
  33. 2025FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inferencecited by 7
  34. 2025Anytime-valid, Bayes-assisted, Prediction-Powered Inferencecited by 7
  35. 2025Probably Approximately Correct Labelscited by 7
  36. 2025Valid Inference with Imperfect Synthetic Datacited by 7
  37. 2025Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personascited by 7
  38. 2026Efficient Inference for Noisy LLM-as-a-Judge Evaluationcited by 7

50 most cited of 214 All 214 (JSON)