Full credit goes to the original author, linked below. All blog posts were reposted either with permission of the author, or by anonymous submission by SAIRC members like yourself.
A research digest of Impey et al. (2024), a University of Arizona study on GPT-4 grading of short student science writing. Notable findings include the comparability of instructor-created and LLM-generated rubrics — and that acceptable grading performance required giving the model both a rubric and an example answer.