利用 LLMs 进行 API 交互:分类和合成数据生成框架

Chunliang Tao, Xiaojing Fan, Yahe Yang
{"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":null,"pages":null},"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\":null,\"pages\":null},\"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。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
LLMs + Persona-Plug = Personalized LLMs MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources Human-like Affective Cognition in Foundation Models
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1