The Bode Family of Large Language Models: Investigating the Frontiers of LLMs in Brazilian Portuguese
Journal of the Brazilian Computer Society · 08.10.2025 · 31 (1) · 918-939
DOI: 10.5753/jbcs.2025.5812 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 08.10.2025. Verfasst von Pedro Henrique Paiola und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid advancement of Large Language Models (LLMs) has significantly impacted Natural Language Processing, yet their effectiveness remains uneven across languages. Most state-of-the-art models are trained predominantly in English, leading to performance disparities in lower-resource languages such as Brazilian Portuguese (BP). This paper explores fine-tuning strategies for adapting open-weight LLMs to BP, focusing on dataset translation techniques, linguistic adaptation challenges, and parameter-efficient fine-tuning methods, such as LoRA and Q-LoRA. We present a benchmark analysis evaluating multiple fine-tuning approaches across various open models, establishing a guiding framework for future BP-specific adaptations. Our results showcase the importance of specialized fine-tuning in improving cross-lingual transfer and NLP performance in BP, contributing to the broader goal of enhancing multilingual language model accessibility.
Zitieren
APA
Paiola, P. H., Garcia, G. L., Correia, J. V. M., Manesco, J. R. R., Garcia, A. L. A., & Papa, J. P. (2025). The Bode Family of Large Language Models: Investigating the Frontiers of LLMs in Brazilian Portuguese. Journal of the Brazilian Computer Society, 31(1), 918-939. https://doi.org/10.5753/jbcs.2025.5812
Vancouver
Paiola PH, Garcia GL, Correia JVM, Manesco JRR, Garcia ALA, Papa JP. The Bode Family of Large Language Models: Investigating the Frontiers of LLMs in Brazilian Portuguese. Journal of the Brazilian Computer Society. 2025;31(1):918-939. doi:10.5753/jbcs.2025.5812
BibTeX
@article{Paiola2025,
author = {Paiola, Pedro Henrique and Garcia, Gabriel Lino and Correia, João Vitor Mariano and Manesco, João Renato Ribeiro and Garcia, Ana Lara Alves and Papa, João Paulo},
title = {The Bode Family of Large Language Models: Investigating the Frontiers of LLMs in Brazilian Portuguese},
journal = {Journal of the Brazilian Computer Society},
year = {2025},
volume = {31},
number = {1},
pages = {918--939},
doi = {10.5753/jbcs.2025.5812}
}
EUVIMED