Saved in:
Bibliographic Details
Main Authors: Le, Hao Duong, Xia, Xin, Xu, Haijie, Zhang, Chen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910258962628608
author Le, Hao Duong
Xia, Xin
Xu, Haijie
Zhang, Chen
author_facet Le, Hao Duong
Xia, Xin
Xu, Haijie
Zhang, Chen
contents Causal discovery aims to identify causal relationships between variables and is a fundamental problem across the sciences. Traditional statistical causal discovery (SCD) methods rely solely on observational data and ignore the contextual information available in metadata, whereas recent LLM-based methods exploit metadata but treat the large language model (LLM) as a single agent, leaving its judgments vulnerable to memorized or biased associations. To address this gap, we introduce MAC (Multi-Agent Causal Discovery Framework), which casts causal discovery as a multi-agent debate coupled with the autonomous selection of an SCD algorithm. MAC combines two complementary modules, bridged by a Meta Fusion mechanism: a Debate-Coding Module (DCM) that grounds an initial graph in data by autonomously selecting and executing the best-suited SCD algorithm, and a Meta-Debate Module (MDM) that refines the graph through an adversarial Affirmative-Negative-Judge debate over the metadata. Across five benchmark datasets and three metrics (F1, SHD, NHD), MAC achieves the best aggregate performance among five statistical and four LLM-based baselines, ranking first on 10 of 15 evaluation points with Gemini-2.0-Flash -- including a perfect reconstruction of the Earthquake graph -- and remains robust across three backbone LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15073
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Causal Discovery Using Large Language Models
Le, Hao Duong
Xia, Xin
Xu, Haijie
Zhang, Chen
Artificial Intelligence
Computation and Language
Causal discovery aims to identify causal relationships between variables and is a fundamental problem across the sciences. Traditional statistical causal discovery (SCD) methods rely solely on observational data and ignore the contextual information available in metadata, whereas recent LLM-based methods exploit metadata but treat the large language model (LLM) as a single agent, leaving its judgments vulnerable to memorized or biased associations. To address this gap, we introduce MAC (Multi-Agent Causal Discovery Framework), which casts causal discovery as a multi-agent debate coupled with the autonomous selection of an SCD algorithm. MAC combines two complementary modules, bridged by a Meta Fusion mechanism: a Debate-Coding Module (DCM) that grounds an initial graph in data by autonomously selecting and executing the best-suited SCD algorithm, and a Meta-Debate Module (MDM) that refines the graph through an adversarial Affirmative-Negative-Judge debate over the metadata. Across five benchmark datasets and three metrics (F1, SHD, NHD), MAC achieves the best aggregate performance among five statistical and four LLM-based baselines, ranking first on 10 of 15 evaluation points with Gemini-2.0-Flash -- including a perfect reconstruction of the Earthquake graph -- and remains robust across three backbone LLMs.
title Multi-Agent Causal Discovery Using Large Language Models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2407.15073