Saved in:
Bibliographic Details
Main Authors: Dawoud, Ahmed, El-Shamy, Osama
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01511
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914233044697088
author Dawoud, Ahmed
El-Shamy, Osama
author_facet Dawoud, Ahmed
El-Shamy, Osama
contents Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to structured covariates, high-dimensional unstructured text often contains rich proxies for these latent variables. This study proposes a Neural Network-Enhanced Double Machine Learning (DML) framework designed to leverage text embeddings for causal identification. Using a rigorous synthetic benchmark, we demonstrate that unstructured text embeddings capture critical confounding information that is absent from structured tabular data. However, we show that standard tree-based DML estimators retain substantial bias (+24%) due to their inability to model the continuous topology of embedding manifolds. In contrast, our deep learning approach reduces bias to -0.86% with optimized architectures, effectively recovering the ground-truth causal parameter. These findings suggest that deep learning architectures are essential for satisfying the unconfoundedness assumption when conditioning on high-dimensional natural language data
format Preprint
id arxiv_https___arxiv_org_abs_2601_01511
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reading Between the Lines: Deconfounding Causal Estimates using Text Embeddings and Deep Learning
Dawoud, Ahmed
El-Shamy, Osama
Artificial Intelligence
Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to structured covariates, high-dimensional unstructured text often contains rich proxies for these latent variables. This study proposes a Neural Network-Enhanced Double Machine Learning (DML) framework designed to leverage text embeddings for causal identification. Using a rigorous synthetic benchmark, we demonstrate that unstructured text embeddings capture critical confounding information that is absent from structured tabular data. However, we show that standard tree-based DML estimators retain substantial bias (+24%) due to their inability to model the continuous topology of embedding manifolds. In contrast, our deep learning approach reduces bias to -0.86% with optimized architectures, effectively recovering the ground-truth causal parameter. These findings suggest that deep learning architectures are essential for satisfying the unconfoundedness assumption when conditioning on high-dimensional natural language data
title Reading Between the Lines: Deconfounding Causal Estimates using Text Embeddings and Deep Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2601.01511