Efficient Causal Graph Discovery Using Large Language Models

Understand

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.