Test-based learning is effective in fostering knowledge retention, but manually creating assessment questions remains time-consuming and limits personalized student practice. The advent of Large Language Models (LLMs) has introduced new possibilities for Automatic Question Generation (AQG). Motivated by this context, this survey provides a comprehensive overview of AQG using LLMs, focusing on educational applications. Following the PRISMA methodology, we reviewed 132 studies published between 2023 and 2025. Our contributions include a taxonomy of question types by response openness, an analysis of AQG efforts across knowledge fields, educational levels, evaluation strategies, and difficulty control. We also identify recurring challenges and research opportunities.
Large Language Models (LLMs) are increasingly being explored for their potential to automate the generation of multiple-choice questions (MCQs). However, the quality of these questions is still influenced by various factors, including pedagogical, conceptual, and linguistic considerations. This article presents the out...
C. Quincozes, D. Molinos, R. Araújo et al.· Revista Brasileira de Inform...· 0 citations
This work proposes SIGFE (Smart Intelligent Generation of Feedback for Education), a modular framework that produces such feedback with LLMs that scales and deals with bias, transparency, and learner agency and sets out what remains to be done on real-time and multimodal delivery.
The overall assessment is that LLMs have significant teaching potential but need to be used with care and backed by evidence to prevent an impact on the ultimate purpose of education.
Jahanara Shaik, P. A. Nandagawali, R. D. Thakare et al.· 2026 10th International Conf...· 0 citations
The use of textbooks as primary sources of information has increasingly given way to tools based on Large Language Models (LLMs), raising concerns about the reliability of generated answers. This study investigates how different adaptation strategies shape the behavior of small language models in educational Question A...
Lucas B. Bulcão Mota, Larrissa Dantas, D. Claro et al.· Brazilian Symposium in Infor...· 0 citations
Language models can analyze and assess student texts using predefined rubrics and deliver structured feedback, reducing instructors'workload. However, existing solutions often rely on external services that are resource-intensive, costly, and raise privacy concerns, making them unsuitable for constrained environments....
S. K. Kafle, Jan Vykopal, Valdemar Švábenský· 0 citations
