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.

翻译：我们提出了一种新颖的框架，利用大型语言模型（LLM）进行完整的因果图发现。尽管先前基于LLM的方法采用成对查询策略，但这需要二次方数量的查询，对于较大规模的因果图会迅速变得不可行。相比之下，所提出的框架采用广度优先搜索（BFS）策略，使其仅需线性数量的查询即可完成任务。我们还证明，当观测数据可用时，该方法能够轻松整合这些数据以提升性能。除了在时间和数据效率上更具优势外，所提出的框架在不同规模的真实世界因果图数据集上均取得了最先进的结果。这些结果证明了该方法在发现因果关系方面的有效性与高效性，展现了其在跨领域因果图发现任务中广泛应用的潜力。