Journal: IPSI Transactions on Internet Research

Generative AI in Audit Oversight:
A Checklist-Based Model Evaluation

Authors: Kresović, Dejana Drulović, Sofija Đoković; Nebojša
and Ćetković, Miloš


View PDF Cite this article

Abstract

This paper examines the use of generative artificial intelligence (GenAI) in audit oversight, with a focus on its role in the preliminary review of the independent auditor's report and accompanying financial statements. Existing audit supervision procedures rely on expert review, which is crucial but also timeconsuming when it is necessary to examine large bodies of documents. The proposed solution is a framework supported by GenAI models, based on checklists, for identifying potential formal, structural and substantive problems in reporting that may require further expert review. The empirical analysis is based on 217 sets of documents of public companies in Serbia for the year 2024. ChatGPT and Gemini 3.1 Pro evaluated the same documents using a structured checklist and a risk scale of 0 to 3, while the expert assessment of audit supervision served as a benchmark. Model performance was evaluated using summary risk scores, mean absolute error, bias, Cohen's kappa coefficient, precision, responsiveness, F1-measure, accuracy, and ROCAUC metrics. The results show that ChatGPT followed a more sensitive review pattern, with higher response and stronger adjusted agreement with the expert benchmark, while Gemini gave more conservative outputs, with higher precision but lower response. Both models performed better in formal and standardized checklist categories than in areas requiring professional judgment, such as key audit issues, business continuity considerations, and internal compliance red flags. The findings suggest that GenAI can support audit oversight by improving the consistency and prioritization of preliminary document review, but only when integrated into a structured framework with expert validation.

Keywords

audit oversight, ChatGPT, expert validation, Gemini, generative AI


Published in: IPSI Transaction on Internet Research (Volume: 22, Issue: 3)
Publisher: IPSI, Belgrade

Date of Publication: July 1, 2026

Open Access: CC-BY-NC-ND
DOI: https://doi.org/10.58245/ipsi.tir.2603.05

Pages: 37 - 45

ISSN: 1820 - 4503

References

1. Malešević, Đ., Čavlin, M., “Poslovna analiza”, Fakultet za ekonomiju i inženjerski menadžment, Novi Sad, 2020.

2. Mishkin, F. S., “The causes and propagation of financial instability: lessons for policy makers”, Federal Reserve Bank, 1997, pp. 55–96.

3. Altman, E., “Financial ratios, discriminant analysis and the prediction of corporate bankruptcy,” Wiley, Journal of Finance 23 (4), 1968, pp. 589–609. https://doi.org/10.2307/ 2978933

4. Kralicek, P., Eine Probe-Excel Auswertung im PDF-Format: Ertrags- und Vermögensanalyse (Quicktest), 2007. Available: http://www.kralicek.at/index.php?gr=-302. Accessed: Feb. 20, 2025

5. Beneish, M. D., “The detection of earnings manipulation,”

6. Čavlin, M., Pešić, M., Pešić, S., “The impact of ratio analysis on the evaluation and management of liquidity in agro-processing companies,” Institute of Agricultural Economics, Ekonomika poljoprivrede 71 (4), 2024, pp. 1299–1312. https://doi.org/10.59267/ekoPolj24041299C

7. Čavlin, M., Vapa Tankosić, J., Jovanović, R., Pavlović, M., “Analysis of the influence of the performance of the profit and financial position in the prediction of bankruptcy in the meat processing branch,” Institute of Agricultural Economics, Ekonomika poljoprivrede 70 (4), 2023. pp. 1043–1057. https://doi.org/10.59267/ekoPolj23041043C

8. Hohnen, P., Ulfstjerne, M.A., Krabbe, M., “Assessing creditworthiness in the age of big data: A comparative study of credit score systems in Denmark and the US,” University of Oslo, Journal of Extreme Anthropology 5 (1), 2021, pp. 29–55. https://doi.org/10.5617/jea.8315

9. Zhen, X., Zhou, Y., “Digital transformation and corporate creditworthiness,” Elsevier, Finance Research Letters 74, 2025, 106742, https://doi.org/10.1016/j.frl.2025.106742

10. World Economic Forum, “The Global Risks Report 2020” (15th ed.), World Economic Forum, 2020. Available: https://www.weforum.org/reports/

...

×

Kresović, Dejana

Dejana Kresović is a doctoral student at the Faculty of Organizational Sciences, University of Belgrade, and is employed at the Securities Commission of the Republic of Serbia in the field of public audit oversight and audit quality control. Her professional work includes the oversight of audit firms and licensed certified auditors, the application of international auditing standards, and the analysis of audit report quality. She is the author of several research papers and has presented at national and international scientific conferences. Her research interests include auditing, public oversight, financial reporting, and the application of generative artificial intelligence.
E-mail: dejana.kresovic@sec.gov.rs, ORCID 0009-0008-9798-0733

×

Drulović, Sofija

Sofija Drulović is a graduate of the Faculty of Organizational Sciences, University of Belgrade, and works as a Junior System Analyst at the Office for Information Technologies and eGovernment of the Republic of Serbia. Her professional focus includes information systems, business analysis, marketing, and strategic problem-solving. During her studies, she was actively involved in the Case Study Club and participated in local, national, and international case study competitions. Her experience includes marketing research, consulting projects, and the preparation of strategic recommendations for business clients. Her professional interests include digital transformation, e-government, business analysis, market research, and the application of artificial intelligence.
E-mail: sofija.vukmirovic@ite.gov.rs, ORCID 0009-0003-7367-3230

× Đoković; Nebojša

Nebojša Đoković holds a MSc in Economics and is an economic affairs adviser at the Association of Montenegrin Banks. He previously worked in banking supervision at the National Bank of Yugoslavia and the Central Bank of Montenegro, and later as an internal auditor at Hipotekarna banka. His professional experience includes banking regulation, financial supervision, internal audit, deposit protection, and European integration in the field of banking and financial services. He is the author of the book Banking of Montenegro and numerous professional articles. His interests include banking, financial services, economic policy, and European financial integration.
E-mail: nebojsa.djokovic@mfa.gov.me, ORCID 0009-0002-9335-1530

×

Ćetković, Miloš

Miloš Cetković holds a degree in Management and a master’s degree in Business Analytics from the Faculty of Organizational Sciences, University of Belgrade. His academic and research interests focus on retail development strategies, omnichannel business models, digital transformation, and the competitiveness of physical stores in the contemporary e-commerce environment. He has more than 25 years of professional experience in trade, retail, and international business. His career includes founding a company for the import and wholesale of computer equipment and developing a retail network of ten physical stores and four online sales channels in Serbia, Montenegro, and Bosnia and Herzegovina.
E-mail: milos.cetkovic@yahoo.com, ORCID 0009-0000-9537-4651

-->
×

Cite this article

Kresović, Dejana; Drulović, Sofija; Nebojša, Đoković and Ćetković, Miloš
"Generative AI in Audit Oversight: A Checklist-Based Model Evaluation",
IPSI Transactions on Internet Research, vol. 22(3), pp. 37-45, 2026, https://doi.org/10.58245/ipsi.tir.2603.05