Elahe Khatibi, Mahyar Abbasian, Zhongqi Yang, Iman Azimi, Amir M. Rahmani
TL;DR通过自动化生成更稳健、准确和可解释的因果图,本研究展示了一种新的框架——自主 LLM(Large Language Models)增强因果推理框架(ALCM),整合了数据驱动的因果推理算法和LLMs,以提高因果推理的效果,并强调了利用LLMs的因果推理能力的新的研究方向。
Abstract
To perform effective causal inference in high-dimensional datasets, initiating the process with causal discovery is imperative, wherein a causal graph is generated based on observational data. However, obtaining