# Causal Inference with Unstructured Treatments

arXiv: https://arxiv.org/abs/2608.00657 · HTML: https://mlsanity.com/paper/2608.00657/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [DoubleMLDeep: Estimation of Causal Effects with Multimodal Data](https://mlsanity.com/paper/2402.01785/) (2024)
- [Leveraging text data for causal inference using electronic health records](https://mlsanity.com/paper/2307.03687/) (2023)
- [A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?](https://mlsanity.com/paper/2510.08758/) (2025)
- [Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data](https://mlsanity.com/paper/2507.03897/) (2025)
- [Text Rationalization for Robust Causal Effect Estimation](https://mlsanity.com/paper/2512.05373/) (2025)
- [Integrating Unstructured Text into Causal Inference: Empirical Evidence from Real Data](https://mlsanity.com/paper/2602.14274/) (2026)
- [Causal Inference with High-Dimensional Treatments](https://mlsanity.com/paper/2602.21423/) (2026)
- [The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice](https://mlsanity.com/paper/2605.01311/) (2026)
- [GenAI Powered Dynamic Causal Inference with Unstructured Data](https://mlsanity.com/paper/2605.07834/) (2026)

## Built on by (most cited first, 1 of 1)

- [Causal Inference with Unstructured Outcomes](https://mlsanity.com/paper/2608.03085/) (2026)

## Abstract (arXiv)

Causal inference usually concerns a scalar treatment, yet in many problems the treatment is unstructured: a text, an image, or a sequence of clinical decisions. Consider an instructor writing a course description to attract more students: the treatment is the course description, and the outcome is enrollment. The standard target, the average treatment effect of fixing the treatment to one exact value versus another, runs into two problems. It cannot be estimated, because almost no exact description recurs across courses, leaving no comparable group from which to measure its effect; and it would be of little use even if it could, since no one wants every course to carry the same description. What the instructor actually wants to know is which features of a description raise enrollment, and which of those features can be acted on across many courses. To this end, we propose a causal query for unstructured treatments: the maximally influential feature (MIF), the feature of the treatment that most strongly influences the outcome. We formalize the MIF as a binary feature of the treatment, defined by a feature-scoring function, constrained so that both of its values stay well populated, and chosen to maximize the causal effect it induces. Turning the feature on shifts the distribution of treatments toward those that display it, turning it off shifts away, and the MIF effect contrasts the two average potential outcomes. We study identification conditions for the MIF, develop algorithms to estimate it, and make it actionable through a nudging algorithm that revises a treatment along the MIF into an outcome-improving version. We illustrate the MIF algorithm across applications in text, image, and dynamic treatment sequences.