Pith. sign in

REVIEW 2 cited by

Vectorizing string entries for data processing on tables: when are larger language models better?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.09634 v1 pith:W7WQ6TS2 submitted 2023-12-15 stat.ML cs.LG

classification stat.MLcs.LG
keywords modelsentrieslanguagedatalargerprocessingtablesbetter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity search. These require converting the data to numbers. While this conversion is easy for simple numerical and categorical entries, databases are strife with text entries, such as names or descriptions. In the age of large language models, what's the best strategies to vectorize tables entries, baring in mind that larger models entail more operational complexity? We study the benefits of language models in 14 analytical tasks on tables while varying the training size, as well as for a fuzzy join benchmark. We introduce a simple characterization of a column that reveals two settings: 1) a dirty categories setting, where strings share much similarities across entries, and conversely 2) a diverse entries setting. For dirty categories, pretrained language models bring little-to-no benefit compared to simpler string models. For diverse entries, we show that larger language models improve data processing. For these we investigate the complexity-performance tradeoffs and show that they reflect those of classic text embedding: larger models tend to perform better, but it is useful to fine tune them for embedding purposes.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Tabular Learners with Context-Aware Semantic Embeddings

    cs.AI 2026-08 conditional novelty 7.0 of 10

    A table-tuned Gemma model with a pre-filled KV cache produces context-aware row embeddings that improve tabular predictors, especially with little training data.

  2. Towards Benchmarking Foundation Models for Tabular Data With Text

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A new 13-dataset benchmark shows that adding text embeddings to tabular models usually improves accuracy, but no embedding or downsampling strategy dominates.

Pith tools