研究人类如何判断表格能否合并，提升数据发现效率。
Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability
- 通过实验分析人类判断表格合并能力的行为模式。
- 基于观察构建机器学习模型，可提升人类原始判断性能。
- 发现人类与大模型结合效果优于单独使用，适合人机协同系统设计。
数据发现，特别是表格合并可行性判断，已成为现代数据科学的关键任务。然而，人类在该过程中的行为仍缺乏深入研究。为此，本研究设计并开展了一项实验调查，对人类判断表格合并可行性的决策过程进行了全面分析。基于分析结果，我们构建了一个机器学习框架，用于提升人类的原始判断性能。此外，我们还初步比较了大语言模型（LLM）与人类的表现，发现结合两者通常优于单一使用。本研究为未来高效的人机协同数据发现系统奠定了基础。
原文摘要 · Abstract (English)
Data discovery and table unionability in particular became key tasks in modern Data Science. However, the human perspective for these tasks is still under-explored. Thus, this research investigates the human behavior in determining table unionability within data discovery. We have designed an experimental survey and conducted a comprehensive analysis, in which we assess human decision-making for table unionability. We use the observations from the analysis to develop a machine learning framework to boost the (raw) performance of humans. Furthermore, we perform a preliminary study on how LLM performance is compared to humans indicating that it is typically better to consider a combination of both. We believe that this work lays the foundations for developing future Human-in-the-Loop systems for efficient data discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。