MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
This addresses the limitation of single-language Program-of-Thought methods for mathematical problem-solving, though it is incremental as it builds on existing PoT frameworks.
The paper tackles the problem of improving mathematical reasoning in LLMs by proposing MultiLingPoT, a method that fine-tunes models on multilingual programming data to use multiple programming languages instead of a single one, resulting in a 6% performance increase compared to single-language PoT with data augmentation.
Program-of-Thought (PoT), which aims to use programming language instead of natural language as an intermediate step in reasoning, is an important way for LLMs to solve mathematical problems. Since different programming languages excel in different areas, it is natural to use the most suitable language for solving specific problems. However, current PoT research only focuses on single language PoT, ignoring the differences between different programming languages. Therefore, this paper proposes an multilingual program reasoning method, MultiLingPoT. This method allows the model to answer questions using multiple programming languages by fine-tuning on multilingual data. Additionally, prior and posterior hybrid methods are used to help the model select the most suitable language for each problem. Our experimental results show that the training of MultiLingPoT improves each program's mathematical reasoning by about 2.5\%. Moreover, with proper mixing, the performance of MultiLingPoT can be further improved, achieving a 6\% increase compared to the single-language PoT with the data augmentation.Resources of this paper can be found at https://github.com/Nianqi-Li/MultiLingPoT.