This study evaluates the ability of large language models (LLMs) to deliver criterion-based grading and examines the impact of prompt engineering with detailed criteria on grading. Using well-established human benchmarks and quantitative analyses, we found that even free LLMs achieve criterion-based grading with a detailed understanding of the…

This study explores how assessment criteria are applied in grading student work. It is found that explicit assessment criteria do not work as authoritative guidance as expected and that tacit criteria are more decisive in awarding a certain grade. Various sources that form idiosyncratic tacit criteria are identified. These sources, including…

The present study examined how information about different grading systems affects students' course expectations, particularly in ways that may have downstream consequences for learning and other academic outcomes. In an online experiment using a preregistered design, we prompted two samples of current and recent college students (N = 547) with a…