Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shen, ChengAo, Chen, Zhengzhang, Luo, Dongsheng, Xu, Dongkuan, Chen, Haifeng, Ni, Jingchao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915314708512768
author Shen, ChengAo
Chen, Zhengzhang
Luo, Dongsheng
Xu, Dongkuan
Chen, Haifeng
Ni, Jingchao
author_facet Shen, ChengAo
Chen, Zhengzhang
Luo, Dongsheng
Xu, Dongkuan
Chen, Haifeng
Ni, Jingchao
contents Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominantly rely on observational data and often overlook the semantic cues inherent in cause-and-effect relationships. The advent of Large Language Models (LLMs) has ushered in an affordable way of leveraging the semantic cues for knowledge-driven causal discovery, but the development of LLMs for causal discovery lags behind other areas, particularly in the exploration of multi-modal data. To bridge the gap, we introduce MATMCD, a multi-agent system powered by tool-augmented LLMs. MATMCD has two key agents: a Data Augmentation agent that retrieves and processes modality-augmented data, and a Causal Constraint agent that integrates multi-modal data for knowledge-driven reasoning. The proposed design of the inner-workings ensures successful cooperation of the agents. Our empirical study across seven datasets suggests the significant potential of multi-modality enhanced causal discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13667
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
Shen, ChengAo
Chen, Zhengzhang
Luo, Dongsheng
Xu, Dongkuan
Chen, Haifeng
Ni, Jingchao
Machine Learning
Artificial Intelligence
Methodology
Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominantly rely on observational data and often overlook the semantic cues inherent in cause-and-effect relationships. The advent of Large Language Models (LLMs) has ushered in an affordable way of leveraging the semantic cues for knowledge-driven causal discovery, but the development of LLMs for causal discovery lags behind other areas, particularly in the exploration of multi-modal data. To bridge the gap, we introduce MATMCD, a multi-agent system powered by tool-augmented LLMs. MATMCD has two key agents: a Data Augmentation agent that retrieves and processes modality-augmented data, and a Causal Constraint agent that integrates multi-modal data for knowledge-driven reasoning. The proposed design of the inner-workings ensures successful cooperation of the agents. Our empirical study across seven datasets suggests the significant potential of multi-modality enhanced causal discovery.
title Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
topic Machine Learning
Artificial Intelligence
Methodology
url https://arxiv.org/abs/2412.13667