# Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects

arXiv: https://arxiv.org/abs/2109.07542 · HTML: https://mlsanity.com/paper/2109.07542/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 70 references that are in the map.
- First posted on arXiv 15 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models](https://mlsanity.com/paper/2106.06087/) (2021)
- [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Double/Debiased/Neyman Machine Learning of Treatment Effects](https://mlsanity.com/paper/1701.08687/) (2017)
- [How to Make Causal Inferences Using Texts](https://mlsanity.com/paper/1802.02163/) (2018)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [Causal Effects of Linguistic Properties](https://mlsanity.com/paper/2010.12919/) (2020)
- [What's Sex Got To Do With Fair Machine Learning?](https://mlsanity.com/paper/2006.01770/) (2020)
- [Challenges of Using Text Classifiers for Causal Inference](https://mlsanity.com/paper/1810.00956/) (2018)
- [Quantifying the Causal Effects of Conversational Tendencies](https://mlsanity.com/paper/2009.03897/) (2020)

## Built on by (most cited first, 3 of 3)

- [Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection](https://mlsanity.com/paper/2205.04238/) (2022)
- [LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding](https://mlsanity.com/paper/2507.02843/) (2025)
- [Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articles](https://mlsanity.com/paper/2606.06715/) (2026)

## Abstract (arXiv)

Using observed language to understand interpersonal interactions is important in high-stakes decision making. We propose a causal research design for observational (non-experimental) data to estimate the natural direct and indirect effects of social group signals (e.g. race or gender) on speakers' responses with separate aspects of language as causal mediators. We illustrate the promises and challenges of this framework via a theoretical case study of the effect of an advocate's gender on interruptions from justices during U.S. Supreme Court oral arguments. We also discuss challenges conceptualizing and operationalizing causal variables such as gender and language that comprise of many components, and we articulate technical open challenges such as temporal dependence between language mediators in conversational settings.