``GenAI-Powered Inference.''

 

  Abstract

We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI leverages open-source Generative Artificial Intelligence (GenAI) models - such as large language models and diffusion models - not only to generate unstructured data at scale but also to extract low-dimensional representations that capture their underlying structure. Applying machine learning to these representations, GPI enables estimation of causal and predictive effects while quantifying associated estimation uncertainty. Unlike existing approaches to representation learning, GPI does not require fine-tuning of generative models, making it computationally efficient and broadly accessible. We illustrate the versatility of the GPI framework through three applications: (1) analyzing Chinese social media censorship, (2) estimating predictive effects of candidates' facial appearance on electoral outcomes, and (3) assessing the persuasiveness of political rhetoric. An open-source software package is available for implementing GPI.

  Software

Imai, Kosuke and Kentaro Nakamura. ``Causal Representation Learning with Generative Artificial Intelligence: Application to Texts as Treatments.''
Nakamura, Kentaro and Kosuke Imai. ``GPI: Generative-AI Powered Inference.'' available through GitHub.

© Kosuke Imai
 Last modified: Tue Jul 8 22:35:39 BST 2025