Automating Turkish Educational Quiz Generation Using Large Language Models
4th International Conference on Intelligent Systems and Pattern Recognition (ISPR 2024), Istanbul, Turkey
Presented on , 20 citations on Google Scholar
In short
The paper introduces Turkish-Quiz-Instruct, a dataset of Turkish educational texts paired with multiple-choice and short-answer questions, and uses GPT-4-Turbo, GPT-3.5-Turbo and Llama-2 models to generate quizzes from Turkish content. The results show these models can produce coherent and relevant Turkish quiz questions.
Cite
@inproceedings{zeinalipour2024automating,
title = {Automating Turkish Educational Quiz Generation Using Large Language Models},
author = {Kamyar Zeinalipour and Yusuf Gökberk Keptiğ and Marco Maggini and Marco Gori},
booktitle = {4th International Conference on Intelligent Systems and Pattern Recognition (ISPR 2024)},
year = {2024},
url = {https://arxiv.org/abs/2406.03397}
}