← Back to all news
arXiv Machine Learning By F\'elix Lefebvre, David Holzm\"uller, Gioia Blayer, Myung Jun Kim, Marine Le Morvan, Ga\"el Varoquaux

TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings

Read the original on arXiv Machine Learning →

TILE (Table-Interfaced LLM Embeddings) bridges large language models (LLMs) and table foundation models (TFMs) to improve tabular learning with string columns. It introduces four key techniques—row serialization, intermediate-layer extraction, columnar pooling, and by-pass features—to extract effective representations from LLMs for tabular data. When combined with TFMs, TILE achieves state‑of‑the‑art performance, outperforming the strongest baseline on 90% of splits across 100 datasets and ranking first on STRABLE’s 108 datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 21

STRABLE: Benchmarking Tabular Machine Learning with Strings

arXiv:2605.12292v2 Announce Type: replace Abstract: Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contai...

By Gioia Blayer, Myung Jun Kim, F\'elix Lefebvre, Lennart Purucker, Alan Arazi, Eilam Shapira, Roi Reichart, Frank Hutter, Marine Le Morvan, David Holzm\"uller, Ga\"el Varoquaux
llmsragbenchmarks
More like this →
arXiv Machine Learning
Jun 4

Towards Pretraining Text Encoders for TabPFN

arXiv:2606. 04876v1 Announce Type: new Abstract: Tabular foundation models, such as TabPFN, achieve strong performance on tabular datasets with numerical and categorical data, but do not natively handle high-cardinality text features.

By Mustafa Tajjar, Alexander Pfefferle, Lennart Purucker, Frank Hutter
llmsragsafety
More like this →
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
llmsragbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 4

Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks

The paper introduces TEmBed, a unified benchmark for evaluating tabular embeddings across four representation levels—cell, row, column, and table—using a diverse set of models. It demonstrates that the best model depends on the specific task and representation level, providing practical guidance for selecting embeddings in real-world applications. The study aims to facilitate the development of more general-purpose tabular representation models.

By Liane Vogel, Kavitha Srinivas, Niharika D'Souza, Sola Shirai, Oktie Hassanzadeh, Horst Samulowitz
ragbenchmarks
More like this →
arXiv Machine Learning
Oct 12

TabMF: Learning Dataset Representations with Tabular Foundation Models

TabMF is a framework that repurposes pretrained tabular foundation models (TFMs) as encoders for supervised datasets, adding a dataset-level readout and fine‑tuning via contrastive post‑training on synthetic views. The authors instantiate TabMF on TabICLv2 and TabPFN‑2.5 and evaluate the resulting representations on six tasks involving unseen real datasets. The approach achieves the best aggregate performance among both learned and classical dataset representations, excelling in dataset retrieval, compact benchmark construction, and distribution‑shift severity assessment.

By Rafiq Kamel, Nicolas Atienza, Aziz Fouch\'e, Nicola Cancedda, Josif Grabocka
benchmarks
More like this →