EUVIMEDEUVIMED entdecken
Crossref

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

Yuan Li, Jun Hu, Bryan Hooi, Bingsheng He, Cheng Chen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15171-15179

DOI: 10.1609/aaai.v40i18.38541 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuan Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 have emerged 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 into 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 industry 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.

Zitieren

APA

Li, Y., Hu, J., Hooi, B., He, B., & Chen, C. (2026). DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15171-15179. https://doi.org/10.1609/aaai.v40i18.38541

Vancouver

Li Y, Hu J, Hooi B, He B, Chen C. DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15171-15179. doi:10.1609/aaai.v40i18.38541

BibTeX
@article{Li2026,
  author = {Li, Yuan and Hu, Jun and Hooi, Bryan and He, Bingsheng and Chen, Cheng},
  title = {DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15171--15179},
  doi = {10.1609/aaai.v40i18.38541}
}
Kostenlos starten →