Using Large Language Models to Support the Audit Process in the Accountability of Interim Managers in Notary Offices

Myke Valadão, Natalia Freire, Mateus de Paula, Lucas Almeida, Leonardo Marques

2025

Abstract

The auditing process in notary offices in Brazil is hindered by inefficiencies, high costs, and the complexity of manual procedures. To address these challenges, we propose a system that leverages the capabilities of Large Language Models (LLMs), specifically LLaMA2-7B and Falcon-7B, to automate critical information extraction from diverse document types. The system detects anomalous monetary values and unauthorized services, linking them to corresponding dates and beneficiaries to provide a detailed overview of financial discrepancies. Integrating advanced Natural Language Processing (NLP) techniques into auditing workflows enhances fraud detection, reduces operational costs, and improves accuracy. With a BLEU metric superior to 0.67, the proposed system demonstrates significant potential to streamline auditing operations. Key benefits include assisting court analysts in identifying fraud cases, optimizing public resource management by eliminating unjustified expenses, and potentially increasing court revenues to reinvest in public services.

Paper Citation

in Harvard Style

Valadão M., Freire N., de Paula M., Almeida L. and Marques L. (2025). Using Large Language Models to Support the Audit Process in the Accountability of Interim Managers in Notary Offices. In Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-749-8, SciTePress, pages 988-995. DOI: 10.5220/0013480900003929

in Bibtex Style

@conference{iceis25,
author={Myke Valadão and Natalia Freire and Mateus de Paula and Lucas Almeida and Leonardo Marques},
title={Using Large Language Models to Support the Audit Process in the Accountability of Interim Managers in Notary Offices},
booktitle={Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2025},
pages={988-995},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013480900003929},
isbn={978-989-758-749-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS
TI - Using Large Language Models to Support the Audit Process in the Accountability of Interim Managers in Notary Offices
SN - 978-989-758-749-8
AU - Valadão M.
AU - Freire N.
AU - de Paula M.
AU - Almeida L.
AU - Marques L.
PY - 2025
SP - 988
EP - 995
DO - 10.5220/0013480900003929
PB - SciTePress