Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese

Maria Carolina Penteado, Fábio Perez

Keywords: grammatical error correction, large language models, gpt-3.5, gpt-4, chatgpt, brazilian portuguese

TL;DR: We investigate the effectiveness of GPT-3.5 and GPT-4 as Grammatical Error Correction (GEC) tools for Brazilian Portuguese and demonstrate that LLMs are promising as GEC tools for Brazilian Portuguese but also pose challenges and limitations.

Abstract: We investigate the effectiveness of GPT-3.5 and GPT-4, two large language models, as Grammatical Error Correction (GEC) tools for Brazilian Portuguese and compare their performance against Microsoft Word and Google Docs. We introduce a GEC dataset for Brazilian Portuguese with four categories: Grammar, Spelling, Internet, and Fast typing. Our results show that while GPT-4 has higher recall than other methods, LLMs tend to have lower precision, leading to overcorrection. This study demonstrates the potential of LLMs as practical GEC tools for Brazilian Portuguese and encourages further exploration of LLMs for non-English languages and other educational settings.

Submission Type: Archival (to be published in the Journal of LatinX in AI (LXAI) Research)

Submission Number: 22