Evaluating the Pedagogical Quality of LLM-Generated Feedback: A Criterion-Based and Comparative Study
A multi-dimension 14-item rating instrument grounded in formative feedback theory is developed and used to compare feedback from a multi-agent system, a single-agent system, and an instructor and shows that a multidimensional approach identifies differences in feedback quality that a single overall rating could miss.
Harvey Ngoe Kolle, Carrie Demmans Epp, Amna Liaqat et al.
· 0 citations