@inproceedings{xu-etal-2024-restful,
    title = "{REST}ful-Llama: Connecting User Queries to {REST}ful {API}s",
    author = "Xu, Han  and
      Zhao, Ruining  and
      Wang, Jindong  and
      Chen, Haipeng",
    editor = "Dernoncourt, Franck  and
      Preo{\c{t}}iuc-Pietro, Daniel  and
      Shimorina, Anastasia",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.emnlp-industry.105/",
    doi = "10.18653/v1/2024.emnlp-industry.105",
    pages = "1433--1443",
    abstract = "Recent advancements in Large Language Models (LLMs) have showcased exceptional performance in zero-shot learning and reasoning tasks. However, integrating these models with external tools - a crucial need for real-world applications - remains a significant challenge. We propose RESTful-Llama, a novel framework designed to enable Llama 3.1 to transform natural language instructions into effective RESTful API calls. To enhance the fine-tuning process, we introduce DOC{\_}Mine, a method to generate fine-tuning datasets from public API documentation. RESTful-Llama distinguishes itself by enabling open-source LLMs to efficiently interact with and adapt to any REST API system. Experiments demonstrate a 31.9{\%} improvement in robustness and a 2.33x increase in efficiency compared to existing methods."
}