Towards Data Science

Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet

Tabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM completes text — and on the TabArena benchmark they now sit above fully tuned gradient-boosted trees. An introduction to how they work, an independent reproduction of the strongest open one, and a map of where XGBoost still wins.

Hugging Face Trending Papers
2d ago

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)

Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to heterogeneous layouts, diverse file formats, and inconsistent organizational conventions. We address two core tasks in spreadsheet understanding: Cell-Type Classification (CTC), which assigns roles to cells, and Table Detection (TD), which identifies table bounding boxes within sheets.

arXiv Machine Learning
1d ago

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)

arXiv:2608. 16050v1 Announce Type: cross Abstract: Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to heterogeneous layouts, diverse file formats, and inconsistent organizational conventions.

By Antoine Gauquier, Ioana Manolescu, Pierre Senellart
arXiv AI
Jun 30

Beyond IID: How General Are Tabular Foundation Models, Really?

arXiv:2606. 30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry.

By Lennart Purucker, Andrej Tschalzev, Nick Erickson, Gioia Blayer, David Holzm\"uller, Alan Arazi, Alexander Pfefferle, Mustafa Tajjar, Ga\"el Varoquaux, Frank Hutter
arXiv AI
Aug 11

Back to the Future: A workbook time machine for spread sheet creation benchmarks

arXiv:2608. 07873v1 Announce Type: new Abstract: We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting).

By Mansi Uniyal, Agamdeep Singh, Ananya Singha, Priyanshu Gupta, Mukul Singh, Gust Verbruggen, Vu Le, Sumit Gulwani
arXiv AI
Jun 30

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

arXiv:2606. 29955v1 Announce Type: cross Abstract: Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making.

By Jian Zhu, Yuzheng Zhang, Zeyao Ma, Bohan Zhang, Armin Schoepf, Daniel Woloch, Peter Yiliu Wang, Guangyu Robert Yang, Samuel Jacob, Siddharth Nagisetty, Abhiram Chundru, Jean Lin, Spencer Mateega, Jing Zhang
arXiv AI
Jun 16

LLMs on Tabular Data with Limited Semantics: Evidence from Industrial Car Retrofit Prediction

arXiv:2606. 15314v1 Announce Type: cross Abstract: Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take.

By Aina Vila Pons, Ioannis Tzachristas, Constantinos Antoniou
arXiv AI
Jul 7

SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks

arXiv:2603. 10002v2 Announce Type: replace-cross Abstract: We consider the task of end-to-end spreadsheet generation, where language models produce spreadsheet artifacts to satisfy users' explicit and implicit constraints, specified in natural language.

By Srivatsa Kundurthy, Clara Na, Michael Handley, Zach Kirshner, Chen Bo Calvin Zhang, Manasi Sharma, Emma Strubell, John Ling