@inproceedings{pei-etal-2025-mathfusion,
    title = "{M}ath{F}usion: Enhancing Mathematical Problem-solving of {LLM} through Instruction Fusion",
    author = "Pei, Qizhi  and
      Wu, Lijun  and
      Pan, Zhuoshi  and
      Li, Yu  and
      Lin, Honglin  and
      Ming, Chenlin  and
      Gao, Xin  and
      He, Conghui  and
      Yan, Rui",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.367/",
    pages = "7400--7420",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) have shown impressive progress in mathematical reasoning. While data augmentation is promising to enhance mathematical problem-solving ability, current approaches are predominantly limited to instance-level modifications{---}such as rephrasing or generating syntactic variations{---}which fail to capture and leverage the intrinsic relational structures inherent in mathematical knowledge. Inspired by human learning processes, where mathematical proficiency develops through systematic exposure to interconnected concepts, we introduce \textbf{MathFusion}, a novel framework that enhances mathematical reasoning through cross-problem instruction synthesis. MathFusion implements this through three fusion strategies: (1) \textit{sequential fusion}, which chains related problems to model solution dependencies; (2) \textit{parallel fusion}, which combines analogous problems to reinforce conceptual understanding; and (3) \textit{conditional fusion}, which creates context-aware selective problems to enhance reasoning flexibility. By applying these strategies, we generate a new dataset, \textbf{MathFusionQA}, followed by fine-tuning models (DeepSeekMath-7B, Mistral-7B, Llama3-8B) on it. Experimental results demonstrate that MathFusion achieves substantial improvements in mathematical reasoning while maintaining high data efficiency, boosting performance by 18.0 points in accuracy across diverse benchmarks while requiring only 45K additional synthetic instructions, representing a substantial improvement over traditional single-instruction approaches."
}