Towards Explainable Transaction Risk Analysis With Dual Graph Retrieval Augmented Generation

ACL ARR 2025 February Submission394 Authors

Abstract:

Explainable transaction risk analysis is a challenge for traditional deep learning models, which only predict suspicious transactions without explanations. Current explainable methods rely on hand-crafted rules and lack the ability to automatically generate language-based explanations. Large Language Models (LLMs) offer promise due to their reasoning and text generation abilities but struggle with domain knowledge and hallucinations, making risk analysis difficult. Specifically, LLMs face: $\textbf{(1) insufficient adaptation to transaction data analysis}$, and $\textbf{(2) ineffective knowledge retrieval methods}$ that ignore the rich graph structure of transaction data.
To address these issues, we propose the $\textbf{Dual}$ $\textbf{G}$raph $\textbf{R}$etrieval-$\textbf{A}$ugmented $\textbf{G}$eneration ($\textbf{Dual-gRAG}$) framework, which utilizes dual retrieval: expert knowledge and reasoning case retrieval. Expert knowledge compensates for domain gaps, while reasoning case retrieval provides step-wise analysis guidance. We incorporate both graph-structured features and semantic features into the retrieval process to enhance the effectiveness of the retrieval. Extensive experiments show that Dual-gRAG improves LLMs’ risk analysis capabilities, achieving a 50\% increase in different metrics.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: Information Retrieval and Text Mining, Question Answering, NLP Applications

Languages Studied: English

Submission Number: 394