TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nobari, Arash Dargahi, Rafiei, Davood
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915450896515072
author Nobari, Arash Dargahi
Rafiei, Davood
author_facet Nobari, Arash Dargahi
Rafiei, Davood
contents The integration of tabular data from diverse sources is often hindered by inconsistencies in formatting and representation, posing significant challenges for data analysts and personal digital assistants. Existing methods for automating tabular data transformations are limited in scope, often focusing on specific types of transformations or lacking interpretability. In this paper, we introduce TabulaX, a novel framework that leverages Large Language Models (LLMs) for multi-class column-level tabular transformations. TabulaX first classifies input columns into four transformation types (string-based, numerical, algorithmic, and general) and then applies tailored methods to generate human-interpretable transformation functions, such as numeric formulas or programming code. This approach enhances transparency and allows users to understand and modify the mappings. Through extensive experiments on real-world datasets from various domains, we demonstrate that TabulaX outperforms existing state-of-the-art approaches in terms of accuracy, supports a broader class of transformations, and generates interpretable transformations that can be efficiently applied.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17110
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations
Nobari, Arash Dargahi
Rafiei, Davood
Databases
Machine Learning
The integration of tabular data from diverse sources is often hindered by inconsistencies in formatting and representation, posing significant challenges for data analysts and personal digital assistants. Existing methods for automating tabular data transformations are limited in scope, often focusing on specific types of transformations or lacking interpretability. In this paper, we introduce TabulaX, a novel framework that leverages Large Language Models (LLMs) for multi-class column-level tabular transformations. TabulaX first classifies input columns into four transformation types (string-based, numerical, algorithmic, and general) and then applies tailored methods to generate human-interpretable transformation functions, such as numeric formulas or programming code. This approach enhances transparency and allows users to understand and modify the mappings. Through extensive experiments on real-world datasets from various domains, we demonstrate that TabulaX outperforms existing state-of-the-art approaches in terms of accuracy, supports a broader class of transformations, and generates interpretable transformations that can be efficiently applied.
title TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations
topic Databases
Machine Learning
url https://arxiv.org/abs/2411.17110