Assessing the quality of automatic-generated short answers using GPT-4

Open-ended assessments play a pivotal role in enabling instructors to evaluate student knowledge acquisition and provide constructive feedback. Integrating large language models (LLMs) such as GPT-4 in educational settings presents a transformative opportunity for assessment methodologies. However,...

詳細記述

書誌詳細

出版年:	Computers and Education: Artificial Intelligence
主要な著者:	Luiz Rodrigues, Filipe Dwan Pereira, Luciano Cabral, Dragan Gašević, Geber Ramalho, Rafael Ferreira Mello
フォーマット:	論文
言語:	英語
出版事項:	Elsevier 2024-12-01
主題:	Automatic answer generation Question-answering Large language models GPT-4 Natural language processing
オンライン･アクセス:	http://www.sciencedirect.com/science/article/pii/S2666920X24000511