• How does the manuscript address issues in accounting and information systems? • Our work can be situated within the interdisciplinary field of research that bridges cutting-edge technologies like process mining with the traditional field of auditing. We have developed a framework, providing comprehensive guidelines for the effective deployment of process mining by internal as well as external auditors. • What are the theoretical underpinnings and why is the theory appropriate for the research question? • Our framework is developed based on the theoretical foundations of the CRISP-DM Process Model and PM 2 . Moreover, to incorporate an auditing perspective throughout our framework, we have tailored each phase of the originally developed framework in alignment with the International Standards on Auditing (ISAs) and Internal Auditing Standards (IPPF PS) and we conducted a comprehensive study with 14 subject matter experts. • Why are the research methods used appropriate for the research question being asked? • Our reliance on the Design Science Research Methodology (DSRM) empowers us to address important practical issues through the creation of our central artifact. We also measured DSR evaluation criteria to assess the overall usefulness and ease of use of our developed artifact with 19 subject matter experts from two Big Four and one Next Ten audit firm. • What makes the research novel, interesting, and defensible? • No established framework exists within the auditing profession outlining overarching implementation guidelines for process mining to conduct audit tasks. We also identified that practitioners call for more guidance regarding how to utilize emerging technologies such as process mining. Furthermore, we evaluated our central artifact with subject matter experts which results ensure the overall usefulness and ease of use of our developed framework. Process Mining (PM) enhances the evaluation of the internal control system with corresponding tests of controls due to a comprehensive analysis of variants within business processes. It can be used by external and internal auditors to improve audit efficiency, effectiveness, and quality. Nevertheless, PM is still not an industry-wide best-practice standard, especially due to existing implementation barriers for practitioners. This study utilizes Design Science Research (DSR) to develop the Audit Process Mining (APM) Framework to implement PM into audit tasks and overcome existing implementation barriers. The APM Framework was designed using empirical insights extracted from interviews with subject matter experts across various audit firms and large industrial companies. Furthermore, 19 auditing professionals confirmed that the APM Framework is a valid and verified solution.

• This study aims to explore the potential of LLMs in external auditing. • We used a mixed-method approach, combining a small survey with qualitative reviews from auditors. • Our findings suggest that auditors perceive LLMs as valuable for performing routine tasks and generating audit working papers. • LLMs enhance audit planning, save time, improve internal control assessment, enhance audit efficiency and effectiveness. • However, concerns persist regarding potential legal liabilities, ethical implications, and hallucinations. This study explores the impact of Large Language Models (LLMs) on external audits and their associated ethical implications. A small-scale survey was conducted with auditors from non-Big Four firms to assess their general perceptions of LLMs, followed by a qualitative evaluation of external LLMs in audit-specific tasks. In the latter, ChatGPT’s responses to audit-related scenarios were assessed by experienced audit partners, who rated and commented on the outputs without knowing their source. The findings indicate that while LLMs efficiently perform routine and mundane tasks such as generating human-like responses and preparing basic audit working papers and reports, external LLMs struggle to produce comprehensive, audit-specific reports. Non-Big Four auditors recognise LLMs’ time-saving potential and relevance in audit planning; however, concerns persist regarding the comprehensiveness and contextual relevance of external LLM-generated risk assessments and interpretations of auditing standards. Moreover, limitations inherent in external LLMs, such as outdated information and hallucinations, necessitate auditor oversight. Ethical concerns identified include threats to auditor objectivity, confidentiality, privacy, accountability, and intellectual property rights. The study reinforces that while LLMs can enhance audit efficiency, they should complement rather than replace auditors. Their successful integration in external audits requires prompt engineering, regulatory guidance, and auditor oversight. These findings contribute to the growing research on LLMs in auditing and provide insights for audit firms considering their adoption.