{"created":"2025-01-19T01:31:24.088168+00:00","updated":"2025-01-19T10:50:38.648591+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231227","sets":["1164:4842:11191:11428"]},"path":["11428"],"owner":"44499","recid":"231227","title":["A Comparative Analysis of Large Language Models for Contextually Relevant Question Generation in Education"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-25"},"_buckets":{"deposit":"30d843fe-55c9-47ad-9494-7fdbd285e529"},"_deposit":{"id":"231227","pid":{"type":"depid","value":"231227","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"A Comparative Analysis of Large Language Models for Contextually Relevant Question Generation in Education","author_link":["623901","623898","623899","623896","623897","623900"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"A Comparative Analysis of Large Language Models for Contextually Relevant Question Generation in Education"},{"subitem_title":"A Comparative Analysis of Large Language Models for Contextually Relevant Question Generation in Education","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"CLE一般セッション(2)","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-11-25","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Faculty of Information Science and Electrical Engineering, Kyushu University"},{"subitem_text_value":"Data-Driven Innovation Initiative, Kyushu University"},{"subitem_text_value":"Faculty of Information Science and Electrical Engineering, Kyushu University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Information Science and Electrical Engineering, Kyushu University","subitem_text_language":"en"},{"subitem_text_value":"Data-Driven Innovation Initiative, Kyushu University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Information Science and Electrical Engineering, Kyushu University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/231227/files/IPSJ-CE23172025.pdf","label":"IPSJ-CE23172025.pdf"},"date":[{"dateType":"Available","dateValue":"2025-11-25"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CE23172025.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"19"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"4093bede-5413-420e-b355-f69f0a7d9bb0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Lodovico, Molina Ivo"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tsubasa, Minematsu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsushi, Shimada"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Lodovico, Molina Ivo","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tsubasa, Minematsu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsushi, Shimada","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10096193","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8930","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"This paper explores the potential of large language models (LLMs) for Automatic Question Generation in educational contexts. We compare three models - GPT-3.5 Turbo, Flan T5 XXL, and Llama 2-Chat 13B - on their ability to generate relevant questions from university slide text without finetuning. Questions were generated in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-Chat 13B; then, questions were generated for each answer by the three models. To evaluate question quality, a survey was conducted where students rated 144 questions across five metrics: clarity, relevance, difficulty, slide relation, and answer correctness. Results showed GPT-3.5 and Llama 2-Chat 13B outperformed Flan T5 XXL overall, with lower scores on clarity and answer-question alignment for Flan T5 XXL. GPT-3.5 excelled at tailoring questions to match input answers. While isolated questions seemed coherent for all models, Llama 2-Chat 13B and Flan T5 XXL showed weaker alignment between generated questions and answers compared to GPT-3.5. This research analyzes the capacity of LLMs for Automatic Question Generation to enhance education, particularly GPT-3.5 and Llama 2-Chat 13B, without any finetuning. Further work is needed to optimize models and methodologies to continually improve question relevance and quality.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper explores the potential of large language models (LLMs) for Automatic Question Generation in educational contexts. We compare three models - GPT-3.5 Turbo, Flan T5 XXL, and Llama 2-Chat 13B - on their ability to generate relevant questions from university slide text without finetuning. Questions were generated in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-Chat 13B; then, questions were generated for each answer by the three models. To evaluate question quality, a survey was conducted where students rated 144 questions across five metrics: clarity, relevance, difficulty, slide relation, and answer correctness. Results showed GPT-3.5 and Llama 2-Chat 13B outperformed Flan T5 XXL overall, with lower scores on clarity and answer-question alignment for Flan T5 XXL. GPT-3.5 excelled at tailoring questions to match input answers. While isolated questions seemed coherent for all models, Llama 2-Chat 13B and Flan T5 XXL showed weaker alignment between generated questions and answers compared to GPT-3.5. This research analyzes the capacity of LLMs for Automatic Question Generation to enhance education, particularly GPT-3.5 and Llama 2-Chat 13B, without any finetuning. Further work is needed to optimize models and methodologies to continually improve question relevance and quality.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータと教育(CE)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"25","bibliographicVolumeNumber":"2023-CE-172"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":231227,"links":{}}