Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
This work addresses the challenge of insufficient observational data for causal discovery in modern systems, offering a more efficient alternative to expert knowledge acquisition.
The authors tackled the problem of learning causality from observational data by proposing a framework that uses multiple large language models (LLMs) to enhance score-based causal discovery methods, resulting in improved performance over single-LLM approaches.
As the significance of understanding the cause-and-effect relationships among variables increases in the development of modern systems and algorithms, learning causality from observational data has become a preferred and efficient approach over conducting randomized control trials. However, purely observational data could be insufficient to reconstruct the true causal graph. Consequently, many researchers tried to utilise some form of prior knowledge to improve causal discovery process. In this context, the impressive capabilities of large language models (LLMs) have emerged as a promising alternative to the costly acquisition of prior expert knowledge. In this work, we further explore the potential of using LLMs to enhance causal discovery approaches, particularly focusing on score-based methods, and we propose a general framework to utilise the capacity of not only one but multiple LLMs to augment the discovery process.