Leveraging Large Language Models for the Automated Generation of Assessment Items Based on Solo Taxonomy

Keywords:
Automatic Question Generation, SOLO Taxonomy, Ontology, LLM

Abstract:
Creating high-quality educational assessment items manually is a laborintensive and cognitively demanding process for educators. This paper introduces an automated system for generating assessment items by integrating the Structure of Observed Learning Outcomes (SOLO) taxonomy with ontology-based knowledge representation. The system automatically extracts hierarchical course structures from learning materials. By leveraging Large Language Models (LLMs), it generates a comprehensive pool of questions that span various cognitive depths, from unistructural to extended abstract, as defined by the SOLO framework. The technical architecture of the system alongside a qualitative pilot evaluation of the generated questions.

CITATION:

IEEE format

Copy to clipboard

U. Petrašković, G. Savić, M. Osmajić, M. Segedinac, P. Steiner, “Leveraging Large Language Models for the Automated Generation of Assessment Items Based on Solo Taxonomy,” in Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2026, pp. 159-164. doi:10.15308/Sinteza-2026-159-164

APA format

Copy to clipboard

Petrašković, U., Savić, G., Osmajić, M., Segedinac, M., Steiner, P. (2026). Leveraging Large Language Models for the Automated Generation of Assessment Items Based on Solo Taxonomy. Paper presented at Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2026-159-164

BibTeX format
Download

RefWorks Tagged format
Download