Discovering and Reasoning of Causality in the Hidden World with Large Language Models

Summary

COAT (Causal representation Assistant) is a framework that uses large language models to propose measured variables for causal discovery from unstructured data. Rather than inferring causality directly, it feeds intermediate causal discovery results back to the LLM to refine those variables. The authors report theoretical guarantees and evaluate the approach on 7 benchmarks and real-world case studies, including analysis of human reviews and diagnosis of neuropathic and brain tumors.