Using AI Large Language Model (LLM-ChatGPT) to Mitigate Spelling Errors of EFL Learners

Despite considerable efforts invested in English language teaching, the prevalence of spelling errors poses a significant obstacle for English as a Foreign Language (EFL) learners due to the intricate nature of the English writing system, which is characterized by a lack of direct, one-to-one correspondence between spoken and written forms. Additionally, the lack of emphasis on developing writing skills exacerbates this issue. Various language learning tasks, such as text generation, machine translation, and long-text summarization, now widely employ Artificial Intelligence Large Language Models (AI-LLMs). This study aims to harness LLM-Generative Pre-training Transformer (GPT) (Language Model GPT) for writing skills to mitigate spelling errors by providing automated feedback, spelling assistance, and opportunities for regular practice. It also aims to gauge the perceptions and attitudes of EFL learners toward using LLM-GPT as a reinforcement approach to minimize spelling errors and improve writing proficiency. A total of 60 EFL students would be involved and a between-subject design method using control and experimental groups would be used in this study. The findings of the study indicated that learners who were taught using LLM_GPT application outscored their counterparts in another group and easily remembered the spelling of words as shown in the post-test session. Moreover, the learners felt the LLM_GPT application had a positive impact on learning spelling of words.