English

Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability

Databases 2025-06-17 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2506.12990,
  title  = {Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability},
  author = {Sreeram Marimuthu and Nina Klimenkova and Roee Shraga},
  journal= {arXiv preprint arXiv:2506.12990},
  year   = {2025}
}

Comments

6 Pages, 4 figures, ACM SIGMOD HILDA '25 (Status-Accepted)

R2 v1 2026-07-01T03:18:43.529Z