# STRABLE: Benchmarking Tabular Machine Learning with Strings

arXiv: https://arxiv.org/abs/2605.12292 · HTML: https://mlsanity.com/paper/2605.12292/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 68 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 18 of 18)

- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [MMTEB: Massive Multilingual Text Embedding Benchmark](https://mlsanity.com/paper/2502.13595/) (2025)
- [A Closer Look at Deep Learning Methods on Tabular Datasets](https://mlsanity.com/paper/2407.00956/) (2024)
- [Benchmarking Multimodal AutoML for Tabular Data with Text Fields](https://mlsanity.com/paper/2111.02705/) (2021)
- [Mambular: A Sequential Model for Tabular Deep Learning](https://mlsanity.com/paper/2408.06291/) (2024)
- [Vectorizing string entries for data processing on tables: when are larger language models better?](https://mlsanity.com/paper/2312.09634/) (2023)
- [Jasper-Token-Compression-600M Technical Report](https://mlsanity.com/paper/2511.14405/) (2025)
- [Tabular Data: Is Deep Learning all you need?](https://mlsanity.com/paper/2402.03970/) (2024)
- [Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks](https://mlsanity.com/paper/2604.21696/) (2026)
- [The Illusion of Generalization in Tabular Language Models](https://mlsanity.com/paper/2602.04031/) (2026)
- [Towards Benchmarking Foundation Models for Tabular Data With Text](https://mlsanity.com/paper/2507.07829/) (2025)

## Built on by (most cited first, 4 of 4)

- [Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI](https://mlsanity.com/paper/2608.16319/) (2026)
- [Enhancing Tabular Learners with Context-Aware Semantic Embeddings](https://mlsanity.com/paper/2608.03565/) (2026)
- [The Silent Failures in Agentic Data Science](https://mlsanity.com/paper/2610.14115/) (2026)
- [TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings](https://mlsanity.com/paper/2610.17065/) (2026)

## Abstract (arXiv)

Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contain string entries, beyond numbers, and these settings have been understudied due to a lack of a solid benchmarking suite. They lead to new research questions: Are dedicated learners needed, with end-to-end modeling of strings and numbers? Or does it suffice to encode strings as numbers, as with a categorical encoding? And if so, do the resulting tables resemble numerical tabular data, calling for the same learners? To enable these studies, we contribute STRABLE, a benchmarking corpus of 108 tables, all real-world learning problems with strings and numbers across diverse application fields. We run the first large-scale empirical study of tabular learning with strings, evaluating 445 pipelines. These pipelines span end-to-end architectures and modular pipelines, where strings are first encoded, then post-processed, and finally passed to a tabular learner. We find that, because most tables in the wild are categorical-dominant, advanced tabular learners paired with simple string embeddings achieve good predictions at low computational cost. On free-text-dominant tables, large LLM encoders become competitive. Their performance also appears sensitive to post-processing, with differences across LLM families. Finally, we show that STRABLE is a good set of tables to study "string tabular" learning as it leads to generalizable pipeline rankings that are close to the oracle rankings. We thus establish STRABLE as a foundation for research on tabular learning with strings, an important yet understudied area.