Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection

TL;DR

This paper introduces MLED, a multi-level LLM-enhanced framework that integrates textual knowledge with graph structures to improve fraud detection accuracy, outperforming existing methods on real-world datasets.

Contribution

The paper proposes a novel multi-level LLM integration framework for graph fraud detection, effectively combining textual and structural data for enhanced performance.

Findings

MLED achieves state-of-the-art results on four real-world datasets.

The framework effectively distinguishes fraudsters from benign entities.

It enhances the importance of fraud-related relations in graph data.

Abstract

Graph fraud detection has garnered significant attention as Graph Neural Networks (GNNs) have proven effective in modeling complex relationships within multimodal data. However, existing graph fraud detection methods typically use preprocessed node embeddings and predefined graph structures to reveal fraudsters, which ignore the rich semantic cues contained in raw textual information. Although Large Language Models (LLMs) exhibit powerful capabilities in processing textual information, it remains a significant challenge to perform multimodal fusion of processed textual embeddings with graph structures. In this paper, we propose a \textbf{M}ulti-level \textbf{L}LM \textbf{E}nhanced Graph Fraud \textbf{D}etection framework called MLED. In MLED, we utilize LLMs to extract external knowledge from textual information to enhance graph fraud detection methods. To integrate LLMs with graph structure information and enhance the ability to distinguish fraudsters, we design a multi-level LLM enhanced framework including type-level enhancer and relation-level enhancer. One is to enhance the difference between the fraudsters and the benign entities, the other is to enhance the importance of the fraudsters in different relations. The experiments on four real-world datasets show that MLED achieves state-of-the-art performance in graph fraud detection as a generalized framework that can be applied to existing methods.