QuerIA: adaptive question generation and evaluation in higher education using large language models and contextual learning

• Presents QuerIA, an open-source system for generating and evaluating Bloom-aligned questions from academic materials. • Combines semantic chunking and prompt-based templates to control difficulty and support multiple-choice and open-ended formats. • Piloted with 341 participants from 17 faculties, generating nearly 6,000 questions and over 800 evaluations. • Results confirm consistent variation in difficulty levels and positive pedagogical perceptions across domains. • Demonstrates the feasibility of local LLM deployment on standard, low-resource hardware, ensuring scalability and data governance in academic settings. This paper presents QuerIA, a system that automates the generation and evaluation of educational questionnaires in Spanish using large language models (LLMs). QuerIA integrates semantic chunking with a simplified Bloom’s taxonomy, enabling controllable variation of cognitive difficulty across multiple-choice (MCQ) and open-ended (OEQ) question formats. Instructional documents are segmented into coherent units, and pedagogically aligned prompts guide the generation of question–answer pairs. The system was deployed as a locally hosted web service at Universidad Politécnica de Madrid, ensuring institutional data governance and low-resource feasibility. During one academic semester, 341 participants from 17 faculties created nearly 6,000 questions and provided more than 800 evaluations on clarity, alignment, and pedagogical value. Analyses show that the predefined difficulty levels correspond to distinct linguistic and psychometric patterns, and that user feedback confirms the clarity and educational usefulness of the generated items. QuerIA demonstrates that LLM-based question generation can be applied at scale in higher education, supporting formative assessment while offering open resources for future research.