Authors:
Vinícius Di Oliveira
1
;
2
;
Yuri Bezerra
2
;
Li Weigang
2
;
Pedro Brom
2
;
3
and
Victor Celestino
4
Affiliations:
1
Secretary of Economy, Brasilia, Federal District, Brazil
;
2
TransLab, University of Brasilia, Brasilia, Federal District, Brazil
;
3
Federal Institute of Brasilia, Brasilia, Federal District, Brazil
;
4
LAMFO, Department of Administration, University of Brasilia, Brasilia, Federal District, Brazil
Keyword(s):
Fine-Tuning, HS, Large Language Model, NCM, Portuguese Language, Retrieval Augmented Generation.
Abstract:
Natural language processing (NLP) has seen significant advancements with the advent of large language models (LLMs). However, substantial improvements are still needed for languages other than English, especially for specific domains like the applications of Mercosur Common Nomenclature (NCM), a Brazilian Harmonized System (HS). To address this gap, this study uses TeenyTineLLaMA, a foundational Portuguese LLM, as an LLM source to implement the NCM application processing. Additionally, a simplified Retrieval-Augmented Fine-Tuning (RAFT) technique, termed SLIM-RAFT, is proposed for task-specific fine-tuning of LLMs. This approach retains the chain-of-thought (CoT) methodology for prompt development in a more concise and streamlined manner, utilizing brief and focused documents for training. The proposed model demonstrates an efficient and cost-effective alternative for fine-tuning smaller LLMs, significantly outperforming TeenyTineLLaMA and ChatGPT-4 in the same task. Although the res
earch focuses on NCM applications, the methodology can be easily adapted for HS applications worldwide.
(More)