Including LLM predictions as covariates in standard regression adjustment for randomized experiments reduces variance with a do-no-harm property that reverts to the unadjusted estimator when predictions are uninformative.
General Synthetic-Powered Inference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
The rapid proliferation of high-quality synthetic data -- generated by advanced AI models or collected as auxiliary data from related tasks -- presents both opportunities and challenges for statistical inference. This paper introduces a GEneral Synthetic-Powered Inference (GESPI) framework that wraps around a broad class of statistical inference procedures to safely enhance sample efficiency by combining synthetic and real data. Our framework leverages high-quality synthetic data to boost statistical power, yet adaptively defaults to the standard method using only real data when synthetic data are of low quality. The error rate of our method remains below a user-specified bound without any distributional assumptions on the synthetic data, and decreases as the quality of the synthetic data improves. This flexibility enables seamless integration with conformal prediction, risk control, hypothesis testing, and multiple testing procedures, all without modifying the base inference method. We demonstrate the benefits of our method on challenging tasks with limited labeled data, including AlphaFold protein structure prediction, and comparing large reasoning models on complex math problems.
years
2026 2representative citing papers
citing papers explorer
-
AI-Assisted Variance Reduction in Randomized Experiments
Including LLM predictions as covariates in standard regression adjustment for randomized experiments reduces variance with a do-no-harm property that reverts to the unadjusted estimator when predictions are uninformative.
- Valid Inference with Synthetic Data via Task Exchangeability