mlsanityData to 14 Oct 2026

Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data

arXiv 2507.03897 ↗First posted 5 Jul 2025cs.LG stat.ME stat.MLcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI leverages open-source Generative Artificial Intelligence (GenAI) models---such as large language models and diffusion models---not only to generate unstructured data at scale but also to extract low-dimensional representations that are guaranteed to capture their underlying structure. Applying machine learning to these representations, GPI enables estimation of causal effects while quantifying associated estimation uncertainty. Unlike existing approaches to representation learning, GPI does not require fine-tuning of generative models, making it computationally efficient and broadly accessible. We illustrate the versatility of the GPI framework through three applications: (1) estimating the effects of Chinese social media censorship while adjusting for textual confounders, (2) isolating the impact of specific image features from that of other correlated features in the same image, and (3) assessing the persuasiveness of political rhetoric. An open-source software package is available for implementing GPI.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 44 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

23 of 44 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  6. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  7. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  8. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
  9. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  10. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
  11. 2023Scaling Sentence Embeddings with Large Language Modelscited by 85
  12. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
11 more
  1. 2018How to Make Causal Inferences Using Textscited by 59
  2. 2020Causal Effects of Linguistic Propertiescited by 39
  3. 2018Matching with Text Data: An Experimental Evaluation of Methods for Matching Documents and of Measuring Match Qualitycited by 21
  4. 2017Protest Activity Detection and Perceived Violence Estimation from Social Media Imagescited by 20
  5. 2024Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatmentscited by 16
  6. 2022Causal Estimation for Text Data with (Apparent) Overlap Violationscited by 15
  7. 2022Conceptualizing Treatment Leakage in Text-based Causal Inferencecited by 14
  8. 2024DoubleMLDeep: Estimation of Causal Effects with Multimodal Datacited by 12
  9. 2024Hyperparameter Tuning for Causal Inference with Double Machine Learning: A Simulation Studycited by 11
  10. 2021Bayesian Topic Regression for Causal Inferencecited by 4
  11. 2025How Much Weak Overlap Can Doubly Robust T-Statistics Handle?cited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Causal Inference with Unstructured Treatmentscited by 1
  2. 2026Causal Inference with Unstructured Outcomescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Narrating Causal Graphs with Large Language Models
  2. 2026Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
  3. 2024Large Language Models and Causal Inference in Collaboration: A Survey
  4. 2023Word-Level Explanations for Analyzing Bias in Text-to-Image Models
  5. 2024Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
  6. 2025Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
  7. 2025Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity
  8. 2026Causal Effect Estimation with Latent Textual Treatments