@inproceedings{zhang-etal-2025-complex,
    title = "Complex Numerical Reasoning with Numerical Semantic Pre-training Framework",
    author = "Zhang, Jun  and
      E, Haihong  and
      Hu, Tianyi  and
      Zhu, Yifan  and
      Song, Meina  and
      Luo, Haoran",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.782/",
    pages = "15491--15525",
    ISBN = "979-8-89176-332-6",
    abstract = "Multi-hop complex reasoning over incomplete knowledge graphs (KGs) has been extensively studied, but research on numerical knowledge graphs (NKGs) remains relatively limited. Recent approaches focus on separately encoding entities and numerical values, using neural networks to process query encodings for reasoning. However, in complex multi-hop reasoning tasks, numerical values are not merely symbols, and they carry specific semantics and logical relationships that must be accurately represented. The CNR-NST framework can perform binary operations on numerical attributes in NKGs, enabling it to infer new numerical attributes from existing knowledge. Our approach effectively handles up to 102 types of complex numerical reasoning queries. On three public datasets, CNR-NST demonstrates SOTA performance in complex numerical queries, achieving an average improvement of over 40{\%} compared to existing methods. Notably, this work expands the query types for complex multi-hop numerical reasoning and introduces a new evaluation metric for numerical answers, which has been validated through comprehensive experiments."
}