Use of Generative Artificial Intelligence in the Development of Educational Assessment Items
Generative Artificial Intelligence, Educational Assessment, Assessment Items, Digital Humanities, Personalized Learning
Digital technologies have transformed teaching and learning practices, and Generative Artificial Intelligence (GAI) emerges as an innovation with the potential to impact educational assessment processes. Large language models enable the automated or semi-automated creation of assessment items, offering possibilities for personalization, scalability, and agile feedback in the educational process. At the same time, challenges arise regarding the validity, reliability, transparency, and equity of such instruments. Framed within the field of Digital Humanities, this research aims to critically investigate the potentialities and challenges of using GAI in the development of assessment items, considering not only technical aspects but also social, cultural, and ethical dimensions. The guiding hypothesis is that GAI can enhance the efficiency and personalization of assessment tools, but it also presents limits and risks that require interdisciplinary and responsible analysis.