一个开放的配方：通过模型合并在一天内将特定语言的LLMs调整为推理模型

An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging

February 13, 2025

作者: Kunat Pipatanakul, Pittawat Taveekitworachai, Potsawee Manakul, Kasima Tharnpipitchai

cs.AI

摘要

本文研究了数据选择和模型合并方法，旨在将类似DeepSeek R1的先进推理能力整合到特定语言的大型语言模型（LLMs）中，特别关注泰语LLM。我们的目标是增强特定语言LLMs的推理能力，同时保持其目标语言能力。DeepSeek R1在推理方面表现出色，但主要受益于英语和中文等高资源语言。然而，由于英语为中心的训练数据和模型优化的主导地位，低资源语言仍未得到充分服务，这限制了这些语言的性能。这种限制导致代码切换不可靠，并且在低资源语言的任务上效果不佳。与此同时，本地和区域LLM倡议已尝试弥合这一差距，通过开发专注于提高本地语言保真度的特定语言LLMs。我们证明，仅凭公开可用的数据集和120美元的计算预算，就可以增强特定语言LLMs的推理能力，使其达到DeepSeek R1的水平，而不会影响其在目标语言任务上的表现。

English

This paper investigates data selection and model merging methodologies aimed at incorporating advanced reasoning capabilities such as those of DeepSeek R1 into language-specific large language models (LLMs), with a particular focus on the Thai LLM. Our goal is to enhance the reasoning capabilities of language-specific LLMs while maintaining their target language abilities. DeepSeek R1 excels in reasoning but primarily benefits high-resource languages such as English and Chinese. However, low-resource languages remain underserved due to the dominance of English-centric training data and model optimizations, which limit performance in these languages. This limitation results in unreliable code-switching and diminished effectiveness on tasks in low-resource languages. Meanwhile, local and regional LLM initiatives have attempted to bridge this gap by developing language-specific LLMs that focus on improving local linguistic fidelity. We demonstrate that, with only publicly available datasets and a computational budget of $120, it is possible to enhance the reasoning capabilities of language-specific LLMs to match the level of DeepSeek R1, without compromising their performance on target language tasks.