Data to 7 Oct 2026

Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates

arXiv 2005.00649 ↗First posted 1 May 2020cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that influence both potential causes and potential effects. Unmeasured or latent confounders can bias causal estimates, and this has motivated interest in measuring potential confounders from observed text. For example, an individual's entire history of social media posts or the content of a news article could provide a rich measurement of multiple confounders. Yet, methods and applications for this problem are scattered across different communities and evaluation practices are inconsistent. This review is the first to gather and categorize these examples and provide a guide to data-processing and evaluation decisions. Despite increased attention on adjusting for confounding using text, there are still many open problems, which we highlight in this paper.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 8; 2024: 13; 2025: 6; 2026: 7.

59 papers.

Sort:

By area:

2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
2022A Causal Lens for Controllable Text Generationcited by 45
2024Causal Inference with Large Language Model: A Surveycited by 31
2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
2022Evaluation Methods and Measures for Causal Learning Algorithmscited by 23
2023COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspectivecited by 22
2021Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLPcited by 21
2023A Causal View of Entity Bias in (Large) Language Modelscited by 21
2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
2022ROCK: Causal Inference Principles for Reasoning about Commonsense Causalitycited by 16
2024Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatmentscited by 16

38 more

2022Causal Estimation for Text Data with (Apparent) Overlap Violationscited by 15
2021Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysiscited by 14
2022Conceptualizing Treatment Leakage in Text-based Causal Inferencecited by 14
2023A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?cited by 14
2022Towards Fine-grained Causal Reasoning and QAcited by 13
2021Enhancing Model Robustness and Fairness with Causality: A Regularization Approachcited by 10
2022A Survey of Deep Causal Models and Their Industrial Applicationscited by 10
2021Generating Synthetic Text Data to Evaluate Causal Inference Methodscited by 9
2023Integrating Earth Observation Data into Causal Inference: Challenges and Opportunitiescited by 8
2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8
2024MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Educationcited by 8
2023RCT Rejection Sampling for Causal Estimation Evaluationcited by 7
2024Proximal Causal Inference With Text Datacited by 7
2024Deep Autoregressive Models as Causal Inference Enginescited by 6
2024CausalTAD: Causal Implicit Generative Model for Debiased Online Trajectory Anomaly Detectioncited by 6
2025Causal Inference on Outcomes Learned from Textcited by 6
2021CausalNLP: A Practical Toolkit for Causal Inference with Textcited by 5
2023Leveraging text data for causal inference using electronic health recordscited by 5
2021What Makes a Scientific Paper be Accepted for Publication?cited by 4
2021Bayesian Topic Regression for Causal Inferencecited by 4
2024Estimating Causal Effects of Text Interventions Leveraging LLMscited by 4
2021Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspectscited by 3
2024Can Large Language Models (or Humans) Disentangle Text?cited by 3
2021A Survey of Online Hate Speech through the Causal Lenscited by 2
2022Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Textscited by 2
2022CKH: Causal Knowledge Hierarchy for Estimating Structural Causal Models from Data and Priorscited by 2
2024Differentiable Pareto-Smoothed Weighting for High-Dimensional Heterogeneous Treatment Effect Estimationcited by 2
2025LLM-Driven Treatment Effect Estimation Under Inference Time Text Confoundingcited by 2
2025A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?cited by 2
2026AI as a Tool for Simulation-Based Experiments in Literary Studiescited by 2
2021Teaching NLP outside Linguistics and Computer Science classrooms: Some challenges and some opportunitiescited by 1
2021Identifying Causal Influences on Publication Trends and Behavior: A Case Study of the Computational Linguistics Communitycited by 1
2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
2024Multi-Task Learning for Features Extraction in Financial Annual Reportscited by 1
2026LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategiescited by 1
2026Using Text-Based Causal Inference to Disentangle Factors Influencing Online Review Ratingscited by 1
2021Causal Discovery in Knowledge Graphs by Exploiting Asymmetric Properties of Non-Gaussian Distributionscited by 0
2021What do writing features tell us about AI papers?cited by 0

50 most cited of 59 All 59 (JSON)