数据准备中迷失:大型语言模型如何处理数据准备?
Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?
AI总结:
本文研究了大型语言模型在数据准备任务中的表现,通过对比传统工具和微调模型,评估其在数据概览和清理方面的有效性。
摘要:
大型语言模型最近展示了在支持和自动化各种任务方面的卓越能力。在测试大型语言模型能力的任务中,我们考虑了数据准备,这是数据驱动过程中的关键但往往劳动密集的步骤。本文调查了大型语言模型是否能有效支持用户在选择和自动化数据准备任务方面。为此,我们考虑了通用和微调的表格大型语言模型。我们用质量差的数据集提示这些模型,并测量它们执行数据概览和清理等任务的能力。我们还比较了大型语言模型提供的支持与传统数据准备工具提供的支持。为了评估大型语言模型的能力,我们开发了一个定制设计的质量模型,该模型通过用户研究验证,以获得对从业者期望的洞察。
英文摘要:
Large language models have recently demonstrated their exceptional capabilities in supporting and automating various tasks. Among the tasks worth exploring for testing large language model capabilities, we considered data preparation, a critical yet often labor-intensive step in data-driven processes. This paper investigates whether large language models can effectively support users in selecting and automating data preparation tasks. To this aim, we considered both general-purpose and fine-tuned tabular large language models. We prompted these models with poor-quality datasets and measured their ability to perform tasks such as data profiling and cleaning. We also compare the support provided by large language models with that offered by traditional data preparation tools. To evaluate the capabilities of large language models, we developed a custom-designed quality model that has been validated through a user study to gain insights into practitioners' expectations.
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。