Enhancing continuous auditing with large language models: AI-assisted real-time accounting information cross-verification

Continuous auditing (CA) faces challenges in analyzing textual data in real time. This study proposes a Large Language Model (LLM)-assisted framework for parsing real-time audit evidence from text to cross-verify accounting data. Following the design science methodology, the three-step framework involves 1) Preprocessing text, 2) LLM inference guided by auditor objectives/schemas and prompts, and 3) Validating accounting records against LLM-derived audit evidence. Demonstrated on a real-life Brazilian governmental payroll system, the framework cross-verifies payroll data with human resources information from the Official Gazette. Compared to auditors’ existing process, the framework improves audit effectiveness through full population testing with cost efficiency, decreases the cross-verification time by 83 percent, and achieves a high accuracy of 96 percent. The study demonstrates the advantage of LLM in facilitating audit quality and contributes by proposing an LLM-assisted framework to facilitate practical CA application.