mlsanityData to 7 Oct 2026

Causal Effects of Linguistic Properties

arXiv 2010.12919 ↗First posted 24 Oct 2020cs.CL cs.AIcited by 39

Not on the map. Why?

Abstract (arXiv)

We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster response time? How much will a positive product review increase sales? This paper addresses two technical challenges related to the problem before developing a practical method. First, we formalize the causal quantity of interest as the effect of a writer's intent, and establish the assumptions necessary to identify this from observational data. Second, in practice, we only have access to noisy proxies for the linguistic properties of interest -- e.g., predictions from classifiers and lexicons. We propose an estimator for this setting and prove that its bias is bounded when we perform an adjustment for the text. Based on these results, we introduce TextCause, an algorithm for estimating causal effects of linguistic properties. The method leverages (1) distant supervision to improve the quality of noisy proxies, and (2) a pre-trained language model (BERT) to adjust for the text. We show that the proposed method outperforms related approaches when estimating the effect of Amazon review sentiment on semi-simulated sales figures. Finally, we present an applied case study investigating the effects of complaint politeness on bureaucratic response times.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 2; 2024: 9; 2025: 6; 2026: 6.

39 papers.

Sort:

By area:

  1. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  2. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  3. 2021Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Predictioncited by 58
  4. 2022Causal Proxy Models for Concept-Based Model Explanationscited by 29
  5. 2021Causal Distillation for Language Modelscited by 19
  6. 2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
  7. 2024Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatmentscited by 16
  8. 2022Causal Estimation for Text Data with (Apparent) Overlap Violationscited by 15
  9. 2022Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxiescited by 13
  10. 2024Towards Compositional Interpretability for XAIcited by 10
  11. 2022FAST: Improving Controllability for Text Generation with Feedback Aware Self-Trainingcited by 7
  12. 2024Proximal Causal Inference With Text Datacited by 7
27 more
  1. 2024Contrastive representations of high-dimensional, structured treatmentscited by 7
  2. 2023Text-Transport: Toward Learning Causal Effects of Natural Languagecited by 6
  3. 2025Preference Learning for AI Alignment: a Causal Perspectivecited by 6
  4. 2021Counterfactual Maximum Likelihood Estimation for Training Deep Networkscited by 5
  5. 2021CausalNLP: A Practical Toolkit for Causal Inference with Textcited by 5
  6. 2023Causal Inference from Text: Unveiling Interactions between Variablescited by 5
  7. 2024Estimating Causal Effects of Text Interventions Leveraging LLMscited by 4
  8. 2021Interventional Aspect-Based Sentiment Analysiscited by 3
  9. 2021Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspectscited by 3
  10. 2021Quantifying the Task-Specific Information in Text-Based Classificationscited by 3
  11. 2022Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Textscited by 2
  12. 2024DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimationcited by 2
  13. 2024Isolated Causal Effects of Natural Languagecited by 2
  14. 2025LLM-Driven Treatment Effect Estimation Under Inference Time Text Confoundingcited by 2
  15. 2025A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?cited by 2
  16. 2021Identifying Causal Influences on Publication Trends and Behavior: A Case Study of the Computational Linguistics Communitycited by 1
  17. 2022Modular Domain Adaptationcited by 1
  18. 2024Causal Inference for Human-Language Model Collaborationcited by 1
  19. 2025Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventionscited by 1
  20. 2026LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategiescited by 1
  21. 2026Using Text-Based Causal Inference to Disentangle Factors Influencing Online Review Ratingscited by 1
  22. 2025Policy Learning with a Natural Language Action Space: A Causal Approachcited by 0
  23. 2025Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Datacited by 0
  24. 2026Causal Effect Estimation with Latent Textual Treatmentscited by 0
  25. 2026Causal Representation Learning for Generalisable Recommendationcited by 0
  26. 2026Causal Risk Minimization for High-Dimensional Treatmentscited by 0
  27. 2026The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Textcited by 0