Technology Convergence (TC)
Fine-tuning and Evaluation of LLaMA Models for Correcting Korean Particle Substitution Errors in Beginner Vietnamese Learners - Focusing on eun/neun (은/는), i/ka (이/가), e (에), and eso (에서)
-
- 발행기관
- 국제문화기술진흥원 바로가기
-
- 간행물
- International Journal of Advanced Culture Technology(IJACT) KCI 등재 바로가기
-
- 통권
- Volume 13 Number 2 (2025.06)바로가기
-
- 페이지
- pp.187-194
-
- 저자
-
- 언어
- 영어(ENG)
-
- URL
- https://www.earticle.net/Article/A469837
※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.
원문정보
초록
- 영어
- Korean grammatical particles present a persistent challenge for Vietnamese learners due to fundamental syntactic differences between the two languages. Vietnamese lacks case-marking particles, often leading to substitution errors involving eun/ neun (은/는), i/ka (이/가), e (에), and eso (에서). Traditional teaching methods offer limited success in addressing these issues. Motivated by the need for more adaptive and learner-sensitive solutions, this paper explores the fine-tuning of the LLaMA 3.2.1B language model to correct Korean particle substitution errors commonly made by beginner Vietnamese learners. A custom dataset was developed by generating simulated learner errors based on authentic sentence structures. The model was fine-tuned using Low-Rank Adaptation (LoRA) and instruction-based prompts to ensure efficiency and contextual accuracy. Evaluation on a 5,800-sentence test set demonstrated a sentence-level accuracy of 91.15%, compared to just 8.36% for the pre-trained baseline. With appropriate fine-tuning, these results endorse the capacity of large language models for providing sound grammatical corrections that are personally suited to the requirements of the learners. This technology exhibits promising potential for intelligent tutoring systems in facilitating one-to-one, real-time feedback in second language learning environments.
목차
Abstract
1. INTRODUCTION
2. RELATED WORK AND BACKGROUND
2.1 Korean Particle Errors Among Vietnamese Learners
2.2 Limitations of Traditional Teaching Methods
2.3 Transitioning to LLaMA: From Traditional GEC to Learner-Focused Fine-Tuning
3. METHODOLOGY
3.1 Workflow
3.2 Method Pipeline
4. EXPERIMENTS
4.1 Preparing a Dataset to Fine-tune LLaMA
4.2 Preparing a Dataset to Fine-tune LLaMA data
4.3 Parameter-Efficient Fine-tuning via LoRA
5. RESULTS AND DISCUSSION
5.1 Training Dynamics: Analysis of Training and Validation Loss
5.2 Manual Testing and Evaluation of Model Performance Across Sentences of Varying Lengths
ACKNOWLEDGEMENT
REFERENCES
키워드
Grammatical Particle LLaMA Model Natural Language Processing Intelligent Tutoring Systems Grammar Error Correction.저자
간행물 정보
발행기관
-
- 발행기관명
- 국제문화기술진흥원 [The International Promotion Agency of Culture Technology]
- 설립연도
- 2009
- 분야
- 공학>공학일반
- 소개
- 본 진흥원은 문화기술(Culture Technology) 관련 산·학·연·관으로 구성된 비영리 단체이다. 문화기술(CT)은 정보통신기술(ICT), 문화적 사고 기반의 예술, 인문학, 디자인, 사회과학기술이 접목된 신융합기술(New Convergence Technology, NCT)로 정의한다. 인간의 삶의 질을 향상시키고, 진보된 방향으로 변화시키고, 문화기술 관련 분야의 학술 및 기술의 발전과 진흥에 공헌하기 위하여, 제3조의 필요한 사업을 행함을 그 목적으로 한다.
간행물
-
- 간행물명
- International Journal of Advanced Culture Technology(IJACT)
- 간기
- 계간
- pISSN
- 2288-7202
- eISSN
- 2288-7318
- 수록기간
- 2013~2025
- 등재여부
- KCI 등재
- 십진분류
- KDC 600 DDC 700
이 권호 내 다른 논문 / International Journal of Advanced Culture Technology(IJACT) Volume 13 Number 2
피인용수 : 0건 (자료제공 : 네이버학술정보)
함께 이용한 논문 이 논문을 다운로드한 분들이 이용한 다른 논문입니다.
0개의 논문이 장바구니에 담겼습니다.