Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis
Text-based causal inference increasingly employs textual data as proxies for unobserved confounders, yet this approach introduces a previously undertheorized source of bias: treatment leakage. Treatment leakage occurs when text intended to capture confounding information also contains signals predictive of treatment status, thereby inducing post-treatment bias in causal estimates. Critically, this problem can arise even when documents precede treatment assignment, as authors may employ future-referencing language that anticipates subsequent interventions. Despite growing recognition of this issue, no systematic methods exist for identifying and mitigating treatment leakage in text-as-confounder applications. This paper addresses this gap through three contributions. First, we provide formal statistical and set-theoretic definitions of treatment leakage that clarify when and why bias occurs. Second, we propose four text distillation methods -- similarity-based passage removal, distant supervision classification, salient feature removal, and iterative nullspace projection -- designed to eliminate treatment-predictive content while preserving confounder information. Third, we validate these methods through simulations using synthetic text and an empirical application examining International Monetary Fund structural adjustment programs and child mortality. Our findings indicate that moderate distillation optimally balances bias reduction against confounder retention, whereas overly stringent approaches degrade estimate precision.
Code (0)
등록된 구현이 없습니다.
Tasks
Causal InferenceSimilar Papers 제목 키워드 기반
Conceptualizing Treatment Leakage in Text-based Causal Inference
Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical…
Causal InferenceConceptualizing Treatment Leakage in Text-based Causal Inference
Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical…
Causal InferenceBounding Causal Effects with Leaky Instruments
Instrumental variables (IVs) are a popular and powerful tool for estimating causal effects in the presence of unobserved confounding. However, classical approaches rely on strong assumptions such as the $\textit{exclusio…
Causal Effect Variational Autoencoder with Uniform Treatment
Domain adaptation and covariate shift are big issues in deep learning and they ultimately affect any causal inference algorithms that rely on deep neural networks. Causal effect variational autoencoder (CEVAE) is trained…
Causal InferenceDomain AdaptationDetecting and Mitigating Group Bias in Heterogeneous Treatment Effects
Heterogeneous treatment effects (HTEs) are increasingly estimated using machine learning models that produce highly personalized predictions of treatment effects. In practice, however, predicted treatment effects are rar…