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

arXiv: https://arxiv.org/abs/2507.21653 · HTML: https://mlsanity.com/paper/2507.21653/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews](https://mlsanity.com/paper/1303.4402/) (2013)
- [Transformers need glasses! Information over-squashing in language tasks](https://mlsanity.com/paper/2406.04267/) (2024)
- [Partitioning Message Passing for Graph Fraud Detection](https://mlsanity.com/paper/2412.00020/) (2024)
- [LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models](https://mlsanity.com/paper/2503.03313/) (2025)
- [Long-Context Generalization with Sparse Attention](https://mlsanity.com/paper/2506.16640/) (2025)
- [Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum](https://mlsanity.com/paper/2312.06441/) (2023)
- [Efficient Heterogeneous Graph Learning via Random Projection](https://mlsanity.com/paper/2310.14481/) (2023)
- [NHAD: Neuro-Fuzzy Based Horizontal Anomaly Detection In Online Social Networks](https://mlsanity.com/paper/1804.06733/) (2018)

## Built on by (most cited first, 12 of 12)

- [CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection](https://mlsanity.com/paper/2605.20032/) (2026)
- [SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management](https://mlsanity.com/paper/2510.08948/) (2025)
- [Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions](https://mlsanity.com/paper/2510.20102/) (2025)
- [Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection](https://mlsanity.com/paper/2605.28524/) (2026)
- [LLM+Graph@VLDB'2025 Workshop Summary](https://mlsanity.com/paper/2604.02861/) (2026)
- [Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs](https://mlsanity.com/paper/2605.24684/) (2026)
- [L2IR: Revealing Latent Intent in Graph Fraud Detection](https://mlsanity.com/paper/2605.26040/) (2026)
- [Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection](https://mlsanity.com/paper/2606.30009/) (2026)
- [Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows](https://mlsanity.com/paper/2607.13078/) (2026)
- [FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection](https://mlsanity.com/paper/2608.15177/) (2026)
- [Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection](https://mlsanity.com/paper/2609.18597/) (2026)
- [FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation](https://mlsanity.com/paper/2610.18023/) (2026)

## Abstract (arXiv)

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.