The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text
Marie Neubrander, Graham Tierney, Alexander Volfovsky
stat.ME, cs.CL, stat.AP, stat.ML
Submitted: 2026-07-28
Project page: https://www.consumerfinance.gov/data-research
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LEACE: Perfect linear concept erasure in closed form
- Causal Estimation for Text Data with (Apparent) Overlap Violations
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- Leveraging text data for causal inference using electronic health records
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
Related papers
- Doubly robust inference via calibration
- Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries
- Weak-Form Recovery of Stochastic Generators
- Optimal Watermark Localization in Mixed-Source Large Language Model Texts
- Optimized Conformal Selection: Powerful Selective Inference After Data-Dependent Score Construction
- Small area learning