Large Languages Models in Brazilian Portuguese: A Chronological Survey

Abstract

The era of Large Language Models (LLMs) started with OpenAI’s GPT-3 model, and the popularity of LLMs has increased exponentially after the introduction of models like ChatGPT and GPT4 that demonstrated remarkable capabilities in natural language processing tasks. LLMs are a special class of pre-trained language models (PLMs) obtained by scaling model size, pretraining corpus, and use of computational power. Large PLMs can be valuable assets, especially for languages such as Portuguese to capture the cultural and knowledge richness inherent in the language. In this sense, this survey encompasses, based on the existing scientific literature, an overview of the research development with LLMs on Brazilian Portuguese (PT-BR-LLMs). The objective is to bring a self-contained, comprehensive overview of PT-BR-LLMs advancements, architectures, and resources. This survey is intended not only to provide a systematic survey but also a quick, comprehensive reference for the research community and practitioners to draw insights from extensive informative summaries of the existing scientific works to advance and progress in the PT-BR-LLMs research field. Considering the emergence of new literature on PT-BR-LLMs, future updates will be made and regularly maintained in the project repository https://github.com/Amadeus-AI-Official/pt-br-llms

Ähnliche Arbeiten