EUVIMEDObjevte EUVIMED
Crossref

Large Language Model-Enhanced Mutual Node-Edge Reinforcement for Inductive Fraud Detection in Financial Systems

Yong Luo, Yan Huang, Songfeng Lu, Xiaofei Yin, Yiting Weng

Intelligent Computing · 2026-01-01 · 5

DOI: 10.34133/icomputing.0365 ↗

At a glance

Journal article in Intelligent Computing, published online on 2026-07-03. Written by Yong Luo and 4 co-authors. 45 references. Funded by: Science, Technology and Innovation Commission of Shenzhen Municipality, Major Research Plan of Hubei Province, Key Research and Development Plan of Hubei Province of China.

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Financial fraud detection requires advanced pattern recognition capabilities to address evolving risks. While existing graph neural networks (GNNs) have improved relational modeling, they still face limitations in synthesizing multi-modal features and handling unseen fraud patterns. This paper proposes large language model-enhanced mutual node-edge reinforcement (LLM-EMNER) for inductive fraud detection in financial systems. Our framework first leverages an LLM to separately generate features for nodes and edges, drawing upon their respective descriptions. Then, we develop an edge-aware graph encoder that dynamically fuses node attributes with transaction edge features through (a) a cross-modal attention mechanism that establishes mutual reinforcement between user nodes and transaction edges, (b) adaptive neighbor selection based on temporal-semantic similarity, and (c) edge-projected feature aggregation that preserves structural patterns. The generated node embeddings are then fed into a softmax classifier fine-tuned with contrastive learning objectives, leveraging the superior capability of contrastive learning in identifying complex fraud patterns from heterogeneous features. The LLM-EMNER component specifically employs a dual-stream architecture where edge features guide node representation updates, while node states refine edge semantics, creating dynamic feature reinforcement. For inductive learning, we design a meta-optimization strategy that enables rapid adaptation to new transaction patterns. The experimental results demonstrate that our method outperforms the baseline GNN methods. The LLM integration provides an average F1-macro improvement of 8.1% in detecting emerging financial fraud patterns compared to the state-of-the-art BWGNN and F2GNN approaches, validating the effectiveness of combining structural graph learning with LLM techniques.

Funding

  • Science, Technology and Innovation Commission of Shenzhen Municipality
  • Major Research Plan of Hubei Province
  • Key Research and Development Plan of Hubei Province of China

Cite

APA

Luo, Y., Huang, Y., Lu, S., Yin, X., & Weng, Y. (2026). Large Language Model-Enhanced Mutual Node-Edge Reinforcement for Inductive Fraud Detection in Financial Systems. Intelligent Computing, 5. https://doi.org/10.34133/icomputing.0365

Vancouver

Luo Y, Huang Y, Lu S, Yin X, Weng Y. Large Language Model-Enhanced Mutual Node-Edge Reinforcement for Inductive Fraud Detection in Financial Systems. Intelligent Computing. 2026;5. doi:10.34133/icomputing.0365

BibTeX
@article{Luo2026,
  author = {Luo, Yong and Huang, Yan and Lu, Songfeng and Yin, Xiaofei and Weng, Yiting},
  title = {Large Language Model-Enhanced Mutual Node-Edge Reinforcement for Inductive Fraud Detection in Financial Systems},
  journal = {Intelligent Computing},
  year = {2026},
  volume = {5},
  doi = {10.34133/icomputing.0365}
}
Start for free →