# TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

arXiv: https://arxiv.org/abs/2606.09323 · HTML: https://mlsanity.com/paper/2606.09323/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 88 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [ExcelFormer: A neural network surpassing GBDTs on tabular data](https://mlsanity.com/paper/2301.02819/) (2023)
- [LakeBench: Benchmarks for Data Discovery over Data Lakes](https://mlsanity.com/paper/2307.04217/) (2023)
- [Unsupervised Embedding Quality Evaluation](https://mlsanity.com/paper/2305.16562/) (2023)
- [Generative Benchmark Creation for Table Union Search](https://mlsanity.com/paper/2308.03883/) (2023)

## Abstract (arXiv)

Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code and data: https://github.com/LOGO-CUHKSZ/TRL-Bench