In the rapidly evolving domain of artificial intelligence, Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs. We meticulously compile a dataset derived from software API documentation and apply fine-tuning to LLMs with capacities of 2B, 3B and 7B parameters, specifically to enhance their proficiency in software API interactions. Our approach concentrates on refining the models' grasp of API structures and syntax, significantly enhancing the accuracy of API function calls. Additionally, we propose \textit{conditional masking} techniques to ensure outputs in the desired formats and reduce error rates while maintaining inference speeds. We also propose a novel benchmark designed to evaluate the effectiveness of LLMs in API interactions, establishing a foundation for subsequent research. Octopus, the fine-tuned model, is proved to have better performance than GPT-4 for the software APIs calling. This research aims to advance automated software development and API integration, representing substantial progress in aligning LLM capabilities with the demands of practical software engineering applications.

利用大型语言模型在软件 API 调用中的提高性能和准确性，通过编译和微调 API 结构和语法，使用条件屏蔽技术确保输出符合预期格式并减少错误率，提出了评估 LLM 在 API 互动中有效性的新基准，并证明了 fine-tuned 模型 Octopus 对于软件 API 调用具有比 GPT-4 更好的性能，推动自动化软件开发和 API 集成的发展，实现了 LLM 能力与实际软件工程应用需求的实质性进展。

八爪鱼：软件API函数调用的设备端语言模型