Abstract

This paper examines the reliability and validity of generative AI in grading academic assignments. Through a literature review and an empirical study, this paper demonstrates that generative AI platforms are currently not a good choice for grading academic assignments due to their inconsistency and unreliability. The study involved repeatedly submitting 12 different papers with varying levels of proficiency to a generative AI platform, revealing significant inconsistencies in grading outcomes.

Download

Share

COinS