Efficient Causal Graph Discovery Using Large Language Models
This addresses a scalability bottleneck for researchers and practitioners in causal inference, though it is incremental over prior LLM-based methods.
The paper tackles the problem of inefficient causal graph discovery with LLMs by proposing a BFS-based framework that reduces queries from quadratic to linear, achieving state-of-the-art results on real-world graphs.
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.