152

AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping

Md Abdul Kadir
Sai Suresh Macharla Vasu
Sidharth S. Nair
Daniel Sonntag
Main:4 Pages
2 Figures
Bibliography:1 Pages
3 Tables
Appendix:3 Pages
Abstract

Auditors rely on Journal Entry Tests (JETs) to detect anomalies in tax-related ledger records, but rule-based methods generate overwhelming false positives and struggle with subtle irregularities. We investigate whether large language models (LLMs) can serve as anomaly detectors in double-entry bookkeeping. Benchmarking SoTA LLMs such as LLaMA and Gemma on both synthetic and real-world anonymized ledgers, we compare them against JETs and machine learning baselines. Our results show that LLMs consistently outperform traditional rule-based JETs and classical ML baselines, while also providing natural-language explanations that enhance interpretability. These results highlight the potential of \textbf{AI-augmented auditing}, where human auditors collaborate with foundation models to strengthen financial integrity.

View on arXiv
Comments on this paper