Milton García-Lima
Author directory2026
Human-in-the-Loop Gemini Item Generation for Large-Scale MCQ Banks
Melchor Sánchez-Mendiola | Milton García-Lima | Elibidú Ortega-Sánchez | Manuel García-Minjares | Enrique Buzo-Casanova
Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
Melchor Sánchez-Mendiola | Milton García-Lima | Elibidú Ortega-Sánchez | Manuel García-Minjares | Enrique Buzo-Casanova
Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
This work-in-progress compares 2,405 Spanish-language MCQs drafted by customized Gemini Gems or faculty in a Mexican university. Expert committees reviewed all items. Gemini drafts showed lower validation-friction in three of four areas and stronger blueprint adherence, while faculty drafts offered richer contextualization. Findings support structured AI generation with human validation.