A Novel Instruction Tuning Method for Vietnamese Mathematical Reasoning using Trainable Open-Source Large Language Models

Nguyen Quang Vinh, Thanh-Do Nguyen, Vinh Van Nguyen, Nam Khac-Hoai Bui


Abstract
This study introduces Simple Reasoning with Code (SiRC), a novel instruction fine-tuning method for solving mathematical reasoning problems, particularly effective for Vietnamese, which is considered a low-resource language. Specifically, solving mathematical problems requires strategic and logical reasoning, which remains challenging in this research area. This paper presents a simple yet effective instruction fine-tuning method for mathematical reasoning. Unlike previous approaches, our proposed method effectively combines chain-of-thought reasoning with code transfer methods without requiring a sophisticated inference procedure. Furthermore, we focus on exploiting small open-source large language models (LLMs) for the Vietnamese language. In this regard, we first introduce a trainable Vietnamese math reasoning dataset, which is named ViMath-InstructCode. The proposed dataset is then used for fine-tuning open-source LLMs (e.g., less than 10 billion parameters). Experiments conducted on our custom ViMath-Bench dataset, the largest benchmarking dataset focusing on Vietnamese mathematical problems, indicate the promising results of our proposed method. Our source code and dataset are available for further exploitation.
Anthology ID:
2024.conll-1.20
Volume:
Proceedings of the 28th Conference on Computational Natural Language Learning
Month:
November
Year:
2024
Address:
Miami, FL, USA
Editors:
Libby Barak, Malihe Alikhani
Venue:
CoNLL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
259–268
Language:
URL:
https://aclanthology.org/2024.conll-1.20
DOI:
Bibkey:
Cite (ACL):
Nguyen Quang Vinh, Thanh-Do Nguyen, Vinh Van Nguyen, and Nam Khac-Hoai Bui. 2024. A Novel Instruction Tuning Method for Vietnamese Mathematical Reasoning using Trainable Open-Source Large Language Models. In Proceedings of the 28th Conference on Computational Natural Language Learning, pages 259–268, Miami, FL, USA. Association for Computational Linguistics.
Cite (Informal):
A Novel Instruction Tuning Method for Vietnamese Mathematical Reasoning using Trainable Open-Source Large Language Models (Vinh et al., CoNLL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.conll-1.20.pdf