Other formats:
BibTeX
LaTeX
RIS
@proceedings{2420777, author = {Lodovico Molina, Ivo and Švábenský, Valdemar and Minematsu, Tsubasa and Chen, Li and Okubo, Fumiya and Shimada, Atsushi}, booktitle = {Proceedings of the 19th European Conference on Technology Enhanced Learning (ECTEL)}, keywords = {Generative AI; Question Generation; AI in Education}, language = {eng}, title = {Comparison of Large Language Models for Generating Contextually Relevant Questions}, url = {https://arxiv.org/abs/2407.20578}, year = {2024} }
TY - CONF ID - 2420777 AU - Lodovico Molina, Ivo - Švábenský, Valdemar - Minematsu, Tsubasa - Chen, Li - Okubo, Fumiya - Shimada, Atsushi PY - 2024 TI - Comparison of Large Language Models for Generating Contextually Relevant Questions KW - Generative AI KW - Question Generation KW - AI in Education UR - https://arxiv.org/abs/2407.20578 N2 - This study explores the effectiveness of Large Language Models (LLMs) for Automatic Question Generation in educational settings. Three LLMs are compared in their ability to create questions from university slide text without fine-tuning. Questions were obtained in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-Chat 13B; then, the three models generated questions for each answer. To analyze whether the questions would be suitable in educational applications for students, a survey was conducted with 46 students who evaluated a total of 246 questions across five metrics: clarity, relevance, difficulty, slide relation, and question-answer alignment. Results indicate that GPT-3.5 and Llama 2-Chat 13B outperform Flan T5 XXL by a small margin, particularly in terms of clarity and question-answer alignment. GPT-3.5 especially excels at tailoring questions to match the input answers. The contribution of this research is the analysis of the capacity of LLMs for Automatic Question Generation in education. ER -
LODOVICO MOLINA, Ivo, Valdemar ŠVÁBENSKÝ, Tsubasa MINEMATSU, Li CHEN, Fumiya OKUBO and Atsushi SHIMADA. Comparison of Large Language Models for Generating Contextually Relevant Questions. In \textit{Proceedings of the 19th European Conference on Technology Enhanced Learning (ECTEL)}. 2024.
|