ALCM: Autonomous LLM-Augmented Causal Discovery Framework
Elahe Khatibi Department of Computer Science, University of California, Irvine, USA Mahyar Abbasian Department of Computer Science, University of California, Irvine, USA Zhongqi Yang Department of Computer Science, University of California, Irvine, USA Iman Azimi Department of Computer Science, University of California, Irvine, USA Amir M. Rahmani Department of Computer Science, University of California, Irvine, USA School of Nursing, University of California, Irvine, USA
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 a complete and accurate causal graph poses a formidable challenge, recognized as an NP-hard problem. Recently, the advent of Large Language Models (LLMs) has ushered in a new era, indicating their emergent capabilities and widespread applicability in facilitating causal reasoning across diverse domains, such as medicine, finance, and science. The expansive knowledge base of LLMs holds the potential to elevate the field of causal reasoning by offering interpretability, making inferences, generalizability, and uncovering novel causal structures. In this paper, we introduce a new framework, named Autonomous LLM-Augmented Causal Discovery Framework (ALCM), to synergize data-driven causal discovery algorithms and LLMs, automating the generation of a more resilient, accurate, and explicable causal graph. The ALCM consists of three integral components: causal structure learning, causal wrapper, and LLM-driven causal refiner. These components autonomously collaborate within a dynam
中文速览
从观测数据中自动推断因果图（causal graph）是因果推断的核心难题，传统数据驱动算法依赖领域专家、对数据质量敏感，而单独使用大语言模型（LLM）又难以处理完整因果图的构建和大规模数据。为此，研究者提出了 ALCM（Autonomous LLM-Augmented Causal Discovery Framework）框架，将传统因果结构学习算法与大语言模型有机结合：先由数据驱动算法学出初步因果图，再经"因果包装器"将图结构转化为语言模型可理解的描述，最后由 LLM 驱动的"因果精炼器"利用模型的先验知识自主修正边的方向与存在性，全程无需人工干预。在七个公认基准数据集上的实验表明，ALCM 在准确性和可解释性方面均优于现有的纯 LLM 方法和传统因果发现算法。这项工作为如何让大语言模型的常识推理能力真正落地到严谨的因果分析流程中提供了可操作的范式，对医疗、金融等需要可靠因果推断的领域具有重要意义。
原文 arXiv:2405.01744;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2405.01744v2