Exploring the use of artificial intelligence (AI) in the delivery of effective feedback

Abstract

Providing effective feedback in large settings presents significant challenges due to time and resource constraints. Given the importance of feedback in competency-based higher education, innovative solutions are essential. This study explores the integration of artificial intelligence (AI) to enhance feedback delivery. The research focuses on the development of a custom prompt for GPT-4 within a no-code web application, designed to deliver AI-generated feedback to second-year accounting students on discussion or essay-style questions in a large competency-based intermediate accounting course in South Africa. The prompt aligns with the principles of effective feedback and was tested in a pilot evaluation. Results indicated that the AI-generated feedback generally adhered to these principles, though some variability was observed across the different feedback dimensions. While challenges remain in consistently guiding AI to apply pedagogical best practices, the findings suggest that large language models can complement traditional feedback. Rigorous oversight of AI-generated feedback remains critical.