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

arXiv: https://arxiv.org/abs/2506.12990 · HTML: https://mlsanity.com/paper/2506.12990/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning](https://mlsanity.com/paper/2210.01922/) (2022)
- [SANTOS: Relationship-based Semantic Table Union Search](https://mlsanity.com/paper/2209.13589/) (2022)
- [Reducing Uncertainty of Schema Matching via Crowdsourcing with Accuracy Rates](https://mlsanity.com/paper/1809.04017/) (2018)
- [Learning to Characterize Matching Experts](https://mlsanity.com/paper/2012.01229/) (2020)
- [PoWareMatch: a Quality-aware Deep Learning Approach to Improve Human Schema Matching](https://mlsanity.com/paper/2109.07321/) (2021)
- [HumanAL: Calibrating Human Matching Beyond a Single Task](https://mlsanity.com/paper/2205.03209/) (2022)

## Built on by (most cited first, 1 of 1)

- [Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making](https://mlsanity.com/paper/2602.11924/) (2026)

## Abstract (arXiv)

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.