@inproceedings{li-etal-2025-multilingpot,
    title = "{M}ulti{L}ing{P}o{T}: Boosting Mathematical Reasoning in {LLM}s through Multilingual Program Integration",
    author = "Li, Nianqi  and
      Liang, Zujie  and
      Yuan, Siyu  and
      Liang, Jiaqing  and
      Wei, Feng  and
      Xiao, Yanghua",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.findings-emnlp.1079/",
    doi = "10.18653/v1/2025.findings-emnlp.1079",
    pages = "19794--19811",
    ISBN = "979-8-89176-335-7",
    abstract = "Program-of-Thought, which aims to use program instead of natural language 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 research only focuses on single language PoT, ignoring the differences between programming languages. Therefore, this paper proposes a multilingual programme reasoning method, MultiLingPoT, and deeply explores the impact of multilingual integration in the training and inference. This method allows the model to answer questions using multiple languages by fine-tuning on multilingual data and improving individual language{'}s reasoning accuracy by 2.5{\%}. Additionally, prior and posterior selection methods are used to help the model select the most suitable language during inference, and achieves 8{\%} performance gains. Finally, our code metric analysis shows that language differences manifest in encapsulation levels and implementation granularity, while strategic deviation from language conventions can enhances code performance."
}