@inproceedings{lazar-etal-2025-generating,
    title = "Generating {O}pen{API} Specifications from Online {API} Documentation with Large Language Models",
    author = "Lazar, Koren  and
      Vetzler, Matan  and
      Kate, Kiran  and
      Tsay, Jason  and
      Boaz, David  and
      Gupta, Himanshu  and
      Shinnar, Avraham  and
      Vallam, Rohith D  and
      Amid, David  and
      Goldbraich, Esther  and
      Laredo, Jim  and
      Anaby Tavor, Ateret",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-industry.18/",
    pages = "237--253",
    ISBN = "979-8-89176-288-6",
    abstract = "AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications. However, the information about APIs available online is often presented as unstructured, free-form HTML documentation, requiring external users to spend significant time manually converting it into a structured format. To address this, we introduce , a novel framework that transforms long and diverse API documentation pages into consistent, machine-readable API specifications. This is achieved through a carefully crafted pipeline that integrates large language models and rule-based algorithms which are guided by domain knowledge of the structure of documentation webpages. Our experiments demonstrate that generalizes well across hundreds of APIs, and produces valid OpenAPI specifications that encapsulate most of the information from the original documentation. has been successfully implemented in an enterprise environment, saving thousands of hours of manual effort and making hundreds of complex enterprise APIs accessible as tools for LLMs."
}