Artificial Intelligence Co-Piloted Auditing

In this study, we propose the concept of artificial intelligence co-piloted auditing, emphasizing the collaborative potential of auditors and foundation models, such as LaMDA, DALL-E, and GPT-4, in the auditing domain. We imagine an audit setup where auditors' capabilities are enhanced through artificial intelligence, facilitating optimal outcomes across a variety of audit tasks. To exemplify the potential of this co-piloted audit paradigm, we illustrate a systematic fine-tuning approach of foundation models using chain-of-thought prompting that enables instruction learning, in-context learning, and sequential reasoning. We demonstrate the potential of co-piloted auditing, by fine-tuning GPT-4 using OpenAI's ChatGPT interface towards three different audit tasks namely financial ratio analysis, text mining, and journal entry testing. We provide a detailed description of the formulated prompt protocols and the corresponding responses generated by ChatGPT, ensuring reproducibility. Our findings underscore the transformative role of foundation models in reshaping the future of auditing and advocate for continued exploration in this area. We envision this work as an initial step towards the widespread implementation of co-piloted auditing, paving the way for more efficient, accurate, and insightful audit procedures