AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914177583415296 |
|---|---|
| author | Kadir, Md Abdul Vasu, Sai Suresh Macharla Nair, Sidharth S. Sonntag, Daniel |
| author_facet | Kadir, Md Abdul Vasu, Sai Suresh Macharla Nair, Sidharth S. Sonntag, Daniel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping Kadir, Md Abdul Vasu, Sai Suresh Macharla Nair, Sidharth S. Sonntag, Daniel Artificial Intelligence 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. |
| title | AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.02726 |