AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping
This addresses the issue of high false positives and subtle irregularities in fraud detection for auditors, offering an AI-augmented approach to enhance financial integrity.
The paper tackled the problem of detecting fraud in double-entry bookkeeping by investigating the use of large language models (LLMs) as anomaly detectors, finding that LLMs consistently outperformed traditional rule-based methods and machine learning baselines while providing natural-language explanations.
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.