Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot

TL;DR

This paper presents CATE-B, an LLM-powered co-pilot system that guides users through causal inference steps, making treatment effect estimation more accessible and reproducible across various domains.

Contribution

Introducing CATE-B, an open-source system that integrates LLMs for causal discovery, adjustment set identification, and method selection, enhancing usability in causal inference.

Findings

CATE-B effectively guides users through causal modeling tasks.

The system improves accuracy in identifying adjustment sets.

Benchmark suite enables reproducibility and evaluation.

Abstract

Estimating treatment effects (TE) from observational data is a critical yet complex task in many fields, from healthcare and economics to public policy. While recent advances in machine learning and causal inference have produced powerful estimation techniques, their adoption remains limited due to the need for deep expertise in causal assumptions, adjustment strategies, and model selection. In this paper, we introduce CATE-B, an open-source co-pilot system that uses large language models (LLMs) within an agentic framework to guide users through the end-to-end process of treatment effect estimation. CATE-B assists in (i) constructing a structural causal model via causal discovery and LLM-based edge orientation, (ii) identifying robust adjustment sets through a novel Minimal Uncertainty Adjustment Set criterion, and (iii) selecting appropriate regression methods tailored to the causal structure and dataset characteristics. To encourage reproducibility and evaluation, we release a suite of benchmark tasks spanning diverse domains and causal complexities. By combining causal inference with intelligent, interactive assistance, CATE-B lowers the barrier to rigorous causal analysis and lays the foundation for a new class of benchmarks in automated treatment effect estimation.