Causality plays a significant role in understanding cause-and-effect relationships, particularly in the context of data-driven decision-making. This research introduces an approach to causal graph generation that combines the power of Large Language Models (LLMs) with classical algorithms from causal theory. In contrast to recent related works that seek to exclude the involvement of domain experts, our method places them at the forefront of the process. We present a novel pipeline that streamlines and enhances expert validation by providing robust causal graph proposals. These proposals are enriched with transparent reports that blend foundational causal theory reasoning with explanations from LLMs. This user-centric approach aims to foster a more comprehensive and reliable causal graph generation process.
weixie-nnu / causalllm-graphgen Goto Github PK
View Code? Open in Web Editor NEWThis project forked from danielepoterti/causalllm-graphgen
This repository focuses on advancing the process of causal graph generation by integrating the capabilities of Large Language Models (LLMs) and time-tested algorithms from causal theory.