When Auditors Trust AI: A Qualitative Study of Professional Judgment, Data Quality, and Adoption Barriers in Lebanon
TL;DR
This study identifies the factors that make auditors either willing or unwilling to trust in AI-powered audit processes and addresses the gap in the literature regarding AI auditing by focusing on the practical conditions for building trust in uncertain audit settings.
Abstract
This study explores auditors’ trust in AI in a limited-resource and turbulent context, namely Lebanon. Using semi-structured interviews with 14 junior and senior auditors in Lebanon, this study identifies the factors that make auditors either willing or unwilling to trust in AI-powered audit processes. The results indicate that auditors perceive the potential benefits of AI, such as increased speed, capacity, and ability to detect anomalies. Yet, trust in AI is limited by concerns about implementation costs, the erosion of professional judgment, blockchain complexity, data overload, and reliance on high-quality data. Instead of excluding AI from the equation, auditors perceive it as tolerable only in conjunction with the role of a person who provides control and supervision, transparent and explainable output, proper management of input data, and established accountability processes. This study addresses the gap in the literature regarding AI auditing by focusing on the practical conditions for building trust in uncertain audit settings