Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability
Marimuthu, Sreeram, Klimenkova, Nina, Shraga, Roee
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jun-17-2025
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > Germany
- Berlin (0.05)
- North America > United States
- Massachusetts > Worcester County
- Worcester (0.04)
- New York > New York County
- New York City (0.04)
- Massachusetts > Worcester County
- Oceania > Fiji (0.04)
- Asia > Middle East
- Genre:
- Research Report > New Finding (0.93)
- Technology: