From Text to Treatment Effects: A Meta-Learning Approach to Handling Text-Based Confounding
This addresses a domain-specific challenge in causal machine learning for researchers and practitioners dealing with text-based confounding, but it is incremental as it builds on existing meta-learning paradigms.
The paper tackled the problem of estimating heterogeneous treatment effects from observational data when confounding variables are expressed in text, showing that meta-learners using pre-trained text representations improve estimates compared to tabular-only methods, but do not match perfect confounder knowledge.
One of the central goals of causal machine learning is the accurate estimation of heterogeneous treatment effects from observational data. In recent years, meta-learning has emerged as a flexible, model-agnostic paradigm for estimating conditional average treatment effects (CATE) using any supervised model. This paper examines the performance of meta-learners when the confounding variables are expressed in text. Through synthetic data experiments, we show that learners using pre-trained text representations of confounders, in addition to tabular background variables, achieve improved CATE estimates compared to those relying solely on the tabular variables, particularly when sufficient data is available. However, due to the entangled nature of the text embeddings, these models do not fully match the performance of meta-learners with perfect confounder knowledge. These findings highlight both the potential and the limitations of pre-trained text representations for causal inference and open up interesting avenues for future research.