• Chung-Ang University

    AI Humanities Research Institute
    HK+ Artificial Intelligence Humanities

›Journals›Article & Issues

Article & Issues

eISSN: 2951-388X
Print ISSN: 2635-4691 / Online ISSN: 2951-388X
Title[JAIH Vol. 19] Implementation of a Korean Language Education Chatbot Using Retrieval-Augmented Generation (RAG) - Focusing on Grammar Correction for Korean Learners_Lee, Seung-Ho·Lee, Chan Kyu2026-11-06 21:47
Writer Level 10
Attachment인공지능 인문학연구 19_02.이승호 이찬규.pdf (1.96MB)

Abstract


The present study addresses the limitations of generative AI, including hallucinations and inadequate handling of specialized domain knowledge, which decrease accuracy in Korean grammar correction and grammatical explanations. To overcome these challenges, this study proposes a Retrieval-Augmented Generation (RAG) API integrated with ChatGPT, utilizing a VectorDB of Korean learners’ error cases and a corpus derived from grammar resources provided by the Korean Language Teaching and Learning Center. The effectiveness of the proposed RAG-based Korean grammar correction chatbot was compared to that of a conventional ChatGPT chatbot, which relied solely on prompt-based instructions. The results demonstrated that the RAG-based chatbot effectively provided learners with precise grammatical expressions suitable for their proficiency level through accurate retrieval from databases. Additionally, the chatbot’s inclusion of source URLs for referenced data enhanced credibility. Therefore, the findings confirm that integrating RAG technology can significantly enhance the quality of generative AI outputs, emphasizing its practical utility and potential for advancing Korean language education.

Chung-Ang University, Humanities Research Institute
#828, 310 Hall, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Korea  TEL +82-2-881-7354  FAX +82-2-813-7353  E-mail : aihumanities@cau.ac.krCOPYRIGHT(C) 2017-2023 CAU HUMANITIES RESEARCH INSTITUTE ALL RIGHTS RESERVED