@inproceedings{li-etal-2026-formulareasoning,
    title = "{F}ormula{R}easoning: A Dataset for Formula-Based Numerical Reasoning",
    author = "Li, Xiao  and
      Zhu, Bolin  and
      Shi, Kaiwen  and
      Liu, Sichen  and
      Zhu, Yin  and
      Liu, Yiwei  and
      Cheng, Gong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1580/",
    pages = "31579--31601",
    ISBN = "979-8-89176-395-1",
    abstract = "The application of physics formulas is a fundamental human capability in numerical reasoning. While existing datasets often rely on implicit mathematical knowledge, they rarely explicitate the underlying formulas. To address this, we introduce FormulaReasoning, a new benchmark for formula-based numerical reasoning comprising 5,324 questions requiring calculations grounded in external physics principles. We provide high-quality, fine-grained annotations in English and Chinese{---}including formula structures, parameter names, symbols, values, and units{---}curated through manual effort and LLM-assisted validation. Additionally, we provide a consolidated formula database as an external knowledge source. To further challenge model performance, we develop an extended version of the dataset by coupling multiple questions. We evaluate various architectural and methodological frameworks, including retrieval-augmented methods, modular reasoning (formula generation, parameter extraction, and calculation), and preference-based optimization. Our analysis identifies critical challenges in formula-based reasoning, highlighting significant opportunities for future methodological advancement."
}