DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs

TL;DR

This paper introduces DGP, a dual-granularity prompting framework that enhances fraud detection with graph-enhanced LLMs by effectively summarizing neighbor information to improve performance and manage token budgets.

Contribution

DGP is the first to apply dual-granularity prompting with tailored summarization strategies for heterogeneous graphs in fraud detection, addressing information overload issues.

Findings

DGP improves fraud detection AUPRC by up to 6.8%.

DGP effectively manages token budgets while maintaining high performance.

Experiments on public and industrial datasets validate DGP's effectiveness.

Abstract

Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features, often rich in textual data, and graph structural information. Recently, Graph-Enhanced LLMs emerge as a promising graph learning approach that converts graph information into prompts, exploiting LLMs' ability to reason over both textual and structural information. Among them, text-only prompting, which converts graph information to prompts consisting solely of text tokens, offers a solution that relies only on LLM tuning without requiring additional graph-specific encoders. However, text-only prompting struggles on heterogeneous fraud-detection graphs: multi-hop relations expand exponentially with each additional hop, leading to rapidly growing neighborhoods associated with dense textual information. These neighborhoods may overwhelm the model with long, irrelevant content in the prompt and suppress key signals from the target node, thereby degrading performance. To address this challenge, we propose Dual Granularity Prompting (DGP), which mitigates information overload by preserving fine-grained textual details for the target node while summarizing neighbor information into coarse-grained text prompts. DGP introduces tailored summarization strategies for different data modalities, bi-level semantic abstraction for textual fields and statistical aggregation for numerical features, enabling effective compression of verbose neighbor content into concise, informative prompts. Experiments across public and industrial datasets demonstrate that DGP operates within a manageable token budget while improving fraud detection performance by up to 6.8% (AUPRC) over state-of-the-art methods, showing the potential of Graph-Enhanced LLMs for fraud detection.