GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning
This work addresses reasoning challenges in Vietnamese language models, which is an incremental improvement for natural language processing in specific domains.
The paper tackles the problem of improving reasoning in Vietnamese large language models by introducing GreenMind-Medium-14B-R1, which uses a finetuning strategy with reward functions to address language mixing and factual correctness, resulting in outperforming prior works on the VLSP 2023 dataset and showing effectiveness on SeaExam.
Chain-of-Thought (CoT) is a robust approach for tackling LLM tasks that require intermediate reasoning steps prior to generating a final answer. In this paper, we present GreenMind-Medium-14B-R1, the Vietnamese reasoning model inspired by the finetuning strategy based on Group Relative Policy Optimization. We also leverage a high-quality Vietnamese synthesized reasoning dataset and design two reward functions to tackle the main limitations of this technique: (i) language mixing, where we explicitly detect the presence of biased language characters during the process of sampling tokens, and (ii) we leverage Sentence Transformer-based models to ensure that the generated reasoning content maintains factual correctness and does not distort the final output. Experimental results on the Vietnamese dataset from the VLSP 2023 Challenge demonstrate that our model outperforms prior works and enhances linguistic consistency in its responses. Furthermore, we extend our evaluation to SeaExam-a multilingual multiple-choice dataset, showing the effectiveness of our reasoning method compared to few-shot prompting techniques.