Efficient Causal Graph Discovery Using Large Language Models

TL;DR

This paper introduces a new LLM-based causal graph discovery framework that uses a BFS approach to reduce queries and incorporate observational data, achieving state-of-the-art results efficiently.

Contribution

It presents a BFS-based method for causal graph discovery with LLMs that is more query-efficient and can integrate observational data, outperforming previous pairwise query approaches.

Findings

Uses linear number of queries instead of quadratic

Incorporates observational data to improve accuracy

Achieves state-of-the-art results on real-world graphs

Abstract

We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the proposed method can easily incorporate observational data when available, to improve performance. In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes. The results demonstrate the effectiveness and efficiency of the proposed method in discovering causal relationships, showcasing its potential for broad applicability in causal graph discovery tasks across different domains.