# Supervised Learning Objectives for High-Dimensional Treatment Effects

arXiv: https://arxiv.org/abs/2605.27281 · HTML: https://mlsanity.com/paper/2605.27281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 24 of 24)

- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [LMPriors: Pre-Trained Language Models as Task-Specific Priors](https://mlsanity.com/paper/2210.12530/) (2022)
- [Approximate Residual Balancing: De-Biased Inference of Average Treatment Effects in High Dimensions](https://mlsanity.com/paper/1604.07125/) (2016)
- [DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training](https://mlsanity.com/paper/1802.05664/) (2018)
- [Generalized Optimal Matching Methods for Causal Inference](https://mlsanity.com/paper/1612.08321/) (2016)
- [Causal Effects of Linguistic Properties](https://mlsanity.com/paper/2010.12919/) (2020)
- [MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance](https://mlsanity.com/paper/2503.13509/) (2025)
- [Challenges of Using Text Classifiers for Causal Inference](https://mlsanity.com/paper/1810.00956/) (2018)
- [Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data](https://mlsanity.com/paper/1904.13335/) (2019)
- [Estimation of causal effects with multiple treatments: a review and new ideas](https://mlsanity.com/paper/1701.05132/) (2017)
- [End-To-End Causal Effect Estimation from Unstructured Natural Language Data](https://mlsanity.com/paper/2407.07018/) (2024)
- [Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments](https://mlsanity.com/paper/2410.00903/) (2024)
- [AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling](https://mlsanity.com/paper/2411.17284/) (2024)
- [Quantifying the Causal Effects of Conversational Tendencies](https://mlsanity.com/paper/2009.03897/) (2020)
- [Adversarial Balancing for Causal Inference](https://mlsanity.com/paper/1810.07406/) (2018)
- [Adversarially Balanced Representation for Continuous Treatment Effect Estimation](https://mlsanity.com/paper/2312.10570/) (2023)
- [End-to-End Balancing for Causal Continuous Treatment-Effect Estimation](https://mlsanity.com/paper/2107.13068/) (2021)
- [Causal Inference from Text: Unveiling Interactions between Variables](https://mlsanity.com/paper/2311.05286/) (2023)
- [Hi-CI: Deep Causal Inference in High Dimensions](https://mlsanity.com/paper/2008.09858/) (2020)
- [Estimating Causal Effects of Text Interventions Leveraging LLMs](https://mlsanity.com/paper/2410.21474/) (2024)
- [Causal Inference with Complex Treatments: A Survey](https://mlsanity.com/paper/2407.14022/) (2024)
- [LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding](https://mlsanity.com/paper/2507.02843/) (2025)

## Abstract (arXiv)

Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call transcript that drives movement in share price, is useful across several domains. However, classical causal estimators tend to assume that all possible interventions are observed, which is infeasible when interventions vary widely, for instance, in the space of all text strings. We adapt a well-known approach of recasting causal inference as a learning problem to address such settings, assuming realizability of the learned function and no unobserved confounding. We show that causal error decomposes into moment-balancing errors of increasing order and exploit structure of the conditional outcome in the confounders to design objectives that directly improve causal estimation. We also show how to project the effect of a high-dimensional treatment onto coarser attributes, which allows a single model to answer several causal questions without additional attribute-specific training. We empirically evaluate our estimators in settings with high-dimensional continuous, discrete, and text treatments. Our experiments demonstrate generalization to held-out treatments, benefits of balancing higher-order moments when required, and projected causal estimates that are competitive with attribute-specific ones.