PaperScope
LIVE · 2026-09-03 05:40 UTC

Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment

Mian Zhong, Katherine A. Keith, Anjalie Field

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.01322 v1
Category
Submitted
2026-09-01

Abstract

In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff in constructing text representations for adjustment: they must be sufficiently large and/or dense to preserve the confounding variables necessary for unbiased effect estimation, but sufficiently small and/or sparse to satisfy finite-sample overlap and yield low-variance estimates. To address this tradeoff, we turn to sparse autoencoders (SAEs), and propose a novel causal adjustment pipeline that iteratively selects a minimal set of SAE features via conditional independence tests. We find that SAE representations achieve better adjustments (lower bias and and higher coverage) than alternative representations in standard semi-synthetic evaluations with binary confounders, and their interpretability offers opportunities for falsification. We also introduce a more realistic semi-synthetic evaluation that uses multi-label data as the unobserved confounders and find off-the-shelf adjustment methods require increased investigation for these more complex settings. Code: https://github.com/mianzg/sae-text-confounder

Comment: Long paper accepted at EMNLP 2026 main conference, 25 pages, 16 figures

arXiv abs page · PDF · same-day batch