Saved in:
Bibliographic Details
Main Authors: Mráz, Martin, Das, Breenda, Gupta, Anshul, Purucker, Lennart, Hutter, Frank
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.07829
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911049403334656
author Mráz, Martin
Das, Breenda
Gupta, Anshul
Purucker, Lennart
Hutter, Frank
author_facet Mráz, Martin
Das, Breenda
Gupta, Anshul
Purucker, Lennart
Hutter, Frank
contents Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strategies for incorporating text into conventional tabular pipelines. Moreover, we benchmark how state-of-the-art tabular foundation models can handle textual data by manually curating a collection of real-world tabular datasets with meaningful textual features. Our study is an important step towards improving benchmarking of foundation models for tabular data with text.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07829
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Benchmarking Foundation Models for Tabular Data With Text
Mráz, Martin
Das, Breenda
Gupta, Anshul
Purucker, Lennart
Hutter, Frank
Machine Learning
Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strategies for incorporating text into conventional tabular pipelines. Moreover, we benchmark how state-of-the-art tabular foundation models can handle textual data by manually curating a collection of real-world tabular datasets with meaningful textual features. Our study is an important step towards improving benchmarking of foundation models for tabular data with text.
title Towards Benchmarking Foundation Models for Tabular Data With Text
topic Machine Learning
url https://arxiv.org/abs/2507.07829