{"title":"利用 LLMs 进行 API 交互:分类和合成数据生成框架","authors":"Chunliang Tao, Xiaojing Fan, Yahe Yang","doi":"arxiv-2409.11703","DOIUrl":null,"url":null,"abstract":"As Large Language Models (LLMs) advance in natural language processing, there\nis growing interest in leveraging their capabilities to simplify software\ninteractions. In this paper, we propose a novel system that integrates LLMs for\nboth classifying natural language inputs into corresponding API calls and\nautomating the creation of sample datasets tailored to specific API functions.\nBy classifying natural language commands, our system allows users to invoke\ncomplex software functionalities through simple inputs, improving interaction\nefficiency and lowering the barrier to software utilization. Our dataset\ngeneration approach also enables the efficient and systematic evaluation of\ndifferent LLMs in classifying API calls, offering a practical tool for\ndevelopers or business owners to assess the suitability of LLMs for customized\nAPI management. We conduct experiments on several prominent LLMs using\ngenerated sample datasets for various API functions. The results show that\nGPT-4 achieves a high classification accuracy of 0.996, while LLaMA-3-8B\nperforms much worse at 0.759. These findings highlight the potential of LLMs to\ntransform API management and validate the effectiveness of our system in\nguiding model testing and selection across diverse applications.","PeriodicalId":501030,"journal":{"name":"arXiv - CS - Computation and Language","volume":"8 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation\",\"authors\":\"Chunliang Tao, Xiaojing Fan, Yahe Yang\",\"doi\":\"arxiv-2409.11703\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As Large Language Models (LLMs) advance in natural language processing, there\\nis growing interest in leveraging their capabilities to simplify software\\ninteractions. In this paper, we propose a novel system that integrates LLMs for\\nboth classifying natural language inputs into corresponding API calls and\\nautomating the creation of sample datasets tailored to specific API functions.\\nBy classifying natural language commands, our system allows users to invoke\\ncomplex software functionalities through simple inputs, improving interaction\\nefficiency and lowering the barrier to software utilization. Our dataset\\ngeneration approach also enables the efficient and systematic evaluation of\\ndifferent LLMs in classifying API calls, offering a practical tool for\\ndevelopers or business owners to assess the suitability of LLMs for customized\\nAPI management. We conduct experiments on several prominent LLMs using\\ngenerated sample datasets for various API functions. The results show that\\nGPT-4 achieves a high classification accuracy of 0.996, while LLaMA-3-8B\\nperforms much worse at 0.759. These findings highlight the potential of LLMs to\\ntransform API management and validate the effectiveness of our system in\\nguiding model testing and selection across diverse applications.\",\"PeriodicalId\":501030,\"journal\":{\"name\":\"arXiv - CS - Computation and Language\",\"volume\":\"8 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computation and Language\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11703\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computation and Language","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11703","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
随着大型语言模型(LLMs)在自然语言处理领域的发展,人们对利用其功能简化软件交互的兴趣与日俱增。通过对自然语言命令进行分类,我们的系统允许用户通过简单的输入调用复杂的软件功能,从而提高交互效率并降低软件使用门槛。我们的数据集生成方法还能对不同的 LLM 在 API 调用分类方面进行高效、系统的评估,为开发人员或企业主评估 LLM 是否适合定制化 API 管理提供了实用工具。我们使用为各种 API 功能生成的样本数据集对几种著名的 LLM 进行了实验。结果表明,GPT-4 的分类准确率高达 0.996,而 LLaMA-3-8B 的分类准确率仅为 0.759,表现要差得多。这些发现凸显了 LLM 在改变 API 管理方面的潜力,并验证了我们的系统在不同应用中指导模型测试和选择的有效性。
Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation
As Large Language Models (LLMs) advance in natural language processing, there
is growing interest in leveraging their capabilities to simplify software
interactions. In this paper, we propose a novel system that integrates LLMs for
both classifying natural language inputs into corresponding API calls and
automating the creation of sample datasets tailored to specific API functions.
By classifying natural language commands, our system allows users to invoke
complex software functionalities through simple inputs, improving interaction
efficiency and lowering the barrier to software utilization. Our dataset
generation approach also enables the efficient and systematic evaluation of
different LLMs in classifying API calls, offering a practical tool for
developers or business owners to assess the suitability of LLMs for customized
API management. We conduct experiments on several prominent LLMs using
generated sample datasets for various API functions. The results show that
GPT-4 achieves a high classification accuracy of 0.996, while LLaMA-3-8B
performs much worse at 0.759. These findings highlight the potential of LLMs to
transform API management and validate the effectiveness of our system in
guiding model testing and selection across diverse applications.