arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09672cs.HCcs.AI
收藏

InstructPipe:利用人类指令和大语言模型生成可视化模块流水线

InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs

Google Research, USA(谷歌研究, 美国);The University of Tokyo, Japan(东京大学, 日本)
Zhongyi Zhou, Jing Jin, Vrushank Phadnis, Xiuxiu Yuan, Jun Jiang, Xun Qian, Kristen Wright, Mark Sherwood, Jason Mayes, Jingtao Zhou, Yiyi Huang, Zheng Xu, Yind… 展开作者

Zhongyi Zhou, Jing Jin, Vrushank Phadnis, Xiuxiu Yuan, Jun Jiang, Xun Qian, Kristen Wright, Mark Sherwood, Jason Mayes, Jingtao Zhou, Yiyi Huang, Zheng Xu, Yinda Zhang, Johnny Lee, Alex Olwal, David Kim, Ram Iyengar, Na Li, Ruofei Du

AI总结:

本文提出InstructPipe,利用大语言模型和代码解释器,通过文本指令生成可视化ML流水线,降低新手学习门槛,提升工作效率并激发创新。

摘要:

可视化编程有潜力为新手程序员提供低代码体验,以构建定制化的处理流水线。现有系统通常要求用户从零开始构建流水线,这意味着新手用户需要从空白工作区中设置并连接合适的节点。在本文中,我们介绍了InstructPipe,一个通过文本指令来原型化机器学习(ML)流水线的AI助手。我们贡献了两个大语言模型(LLM)模块和一个代码解释器作为我们框架的一部分。LLM模块为目标流水线生成伪代码,解释器则在节点图编辑器中渲染流水线,以进一步进行人机协作。技术评估和用户评估(N=16)均表明,InstructPipe使用户能够简化其ML流水线工作流程,降低学习曲线,并利用开放式命令激发创新想法。

英文摘要:

Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines. Existing systems typically require users to build pipelines from scratch, implying that novice users are expected to set up and link appropriate nodes from a blank workspace. In this paper, we introduce InstructPipe, an AI assistant for prototyping machine learning (ML) pipelines with text instructions. We contribute two large language model (LLM) modules and a code interpreter as part of our framework. The LLM modules generate pseudocode for a target pipeline, and the interpreter renders the pipeline in the node-graph editor for further human-AI collaboration. Both technical and user evaluation (N=16) shows that InstructPipe empowers users to streamline their ML pipeline workflow, reduce their learning curve, and leverage open-ended commands to spark innovative ideas.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑