XI INTERNATIONAL CONFERENCE
“INFORMATION TECHNOLOGY AND IMPLEMENTATION” (IT&I-2024)
Features of the practical use of LLM for generating quiz
Oleh Ilarionov , Hanna Krasovska , �Iryna Domanetska , Olena Fedusenko
The potential of LLM in education
Переваги LLM в освіті:
Моделі, використані у дослідженні:
Приклади можливостей:
A query optimisation
Query optimisation for generating high-quality test tasks :
Algorithm for forming an optimal query
Limitations of models in quiz generation
Оптимізація запиту для генерації якісних завдань:
Research models and tools
Models : GPT, Claude, Copilot та Gemini.
A fragment of lecture material :
Main evaluation criteria :
Comparative analysis of models
Comparative analysis of models
Parameter | GPT | Claude | Δ |
Average question length (characters) | 85 | 110 | -25 |
Average length of justification (characters) | 120 | 150 | -30 |
Median number of words per question | 15 | 18 | -3 |
Quality of created tasks
Criterion | GPT | Claude | Δ |
Content validity | 4.5 | 4.5 | 0 |
Construct validity | 4.0 | 4.5 | +0.5 |
Clarity of wording | 4.5 | 4.5 | 0 |
No ambiguity | 4.0 | 4.5 | +0.5 |
Relevance of answer options | 4.5 | 4.5 | 0 |
Cognitive level (according to Bloom) | 3.5 | 4.0 | +0.5 |
Average score | 4.17 | 4.42 | +0.25 |
Conclusion
THANK YOU FOR ATTENTION