arXiv AI July 17, 2026 By Yichen Xu

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities

arXiv:2604. 23904v3 Announce Type: replace-cross Abstract: Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Sep 10

Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomes

arXiv:2609.06294v1 Announce Type: new Abstract: Estimating conditional average treatment effects (CATE) enables efficient targeting of interventions, but many applications have limited experimental s...

By Maitreyi Swaroop, Shikha Bhat, Samantha Rodriguez, Tamar Krishnamurti, Bryan Wilder

safety

arXiv Machine Learning

Jul 10

Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration

arXiv:2607. 08122v1 Announce Type: new Abstract: Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic records.

By Amir Asiaee, Kaveh Aryan

safety

arXiv Machine Learning

Jul 27

LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategies

arXiv:2604. 16763v3 Announce Type: replace Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goals of care, and mental status are documented in free-text notes but absent from structured data.

By Lei Liu, Jialin Chen, Kathy Macropol

llms nlp safety

arXiv Machine Learning

Jul 10

Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

arXiv:2603. 19186v3 Announce Type: replace Abstract: Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect heterogeneity.

By Amir Asiaee, Samhita Pal

rag safety

arXiv Machine Learning

Jun 5

Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction

arXiv:2606. 05797v1 Announce Type: new Abstract: Longitudinal treatment decisions require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data.

By Amirhossein Zare, Amirhessam Zare, Herlock Rahimi, Reza Salarikia, Mohammad Kashkooli

benchmarks

arXiv Machine Learning

Jul 8

Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure

arXiv:2603. 10254v2 Announce Type: replace Abstract: Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains.

By Davide Tugnoli, Andrea De Lorenzo, Marco Virgolin, Giovanni Cin\`a

benchmarks safety data-engineering

One email a morning, machine-written

Related stories

Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomes

Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration

LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategies

Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction

Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure