Tabular learning needs cross-validation across hundreds of tables, researcher says

GaelVaroquaux · x · 2026-07-26

Gael Varoquaux says tabular learning evaluation is still badly done: serious evaluation requires cross-validation across hundreds of tables, each with thousands or even hundreds of thousands of rows.

He argues that past failures to evaluate properly have contributed to stagnation in the field, and that model size alone is not the right question. The reply thread jokes about how large a model would satisfy reviewers, but the core point is that rigorous evaluation methodology matters more than chasing scale.

Related event: Researchers Discuss PFNs vs Post-trained LLMs for Tabular Data(4 posts)→

Original post →

More from Research

Research channel →