GenAI Powered Dynamic Causal Inference with Unstructured Data
Abstract
A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text.
Related
- Leveraging generative AI for causal inference with unstructured data
- Surrogate-powered Causal Inference with Censored Outcomes
- Whole-brain modeling of dynamic causal circuits in human cognition using amortized variational inference
- Semiparametric Inference for Dynamic Causal Effects from Observational Time Series
- Identifying ODEs from Unstructured Data with Causal Representation Learning
BibTeX
@misc{nakamura2026genai,
title = {{GenAI Powered Dynamic Causal Inference with Unstructured Data}},
author = {Kentaro Nakamura and Kosuke Imai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.07834},
eprint = {2605.07834},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.07834},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - GenAI Powered Dynamic Causal Inference with Unstructured Data
AU - Kentaro Nakamura
AU - Kosuke Imai
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2605.07834
UR - https://arxiv.org/abs/2605.07834
AB - A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text.
ER -