Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning
A multi-agent semantic enrichment framework that generates interpretable financial semantics grounded in transaction behavior through role-specialized agents and consistency refinement is proposed and newly contribute a valuable multimodal financial fraud dataset, MS-FFSD, enriched with structured semantics and textual...
Lin-Bo Shao, Hui-Lin He, Yating Lou et al.
· 0 citations