Automatic End-to-End Data Integration using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Steiner, Aaron, Bizer, Christian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915853695451136
author Steiner, Aaron
Bizer, Christian
author_facet Steiner, Aaron
Bizer, Christian
contents Designing data integration pipelines typically requires substantial manual effort from data engineers to configure pipeline components and label training data. While LLMs have shown promise in handling individual steps of the integration process, their potential to replace all human input across end-to-end data integration pipelines has not been investigated. As a step toward exploring this potential, we present an automatic data integration pipeline that uses GPT-5.2 to generate all artifacts required to adapt the pipeline to specific use cases. These artifacts are schema mappings, value mappings for data normalization, training data for entity matching, and validation data for selecting conflict resolution heuristics in data fusion. We compare the performance of this LLM-based pipeline to the performance of human-designed pipelines along three case studies requiring the integration of video game, music, and company related data. Our experiments show that the LLM-based pipeline is able to produce similar results, for some tasks even better results, as the human-designed pipelines. End-to-end, the human and the LLM pipelines produce integrated datasets of comparable size and density. Having the LLM configure the pipelines costs approximately \$10 per case study, which represents only a small fraction of the cost of having human data engineers perform the same tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10547
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic End-to-End Data Integration using Large Language Models
Steiner, Aaron
Bizer, Christian
Computation and Language
H.2.5; I.2.7
Designing data integration pipelines typically requires substantial manual effort from data engineers to configure pipeline components and label training data. While LLMs have shown promise in handling individual steps of the integration process, their potential to replace all human input across end-to-end data integration pipelines has not been investigated. As a step toward exploring this potential, we present an automatic data integration pipeline that uses GPT-5.2 to generate all artifacts required to adapt the pipeline to specific use cases. These artifacts are schema mappings, value mappings for data normalization, training data for entity matching, and validation data for selecting conflict resolution heuristics in data fusion. We compare the performance of this LLM-based pipeline to the performance of human-designed pipelines along three case studies requiring the integration of video game, music, and company related data. Our experiments show that the LLM-based pipeline is able to produce similar results, for some tasks even better results, as the human-designed pipelines. End-to-end, the human and the LLM pipelines produce integrated datasets of comparable size and density. Having the LLM configure the pipelines costs approximately \$10 per case study, which represents only a small fraction of the cost of having human data engineers perform the same tasks.
title Automatic End-to-End Data Integration using Large Language Models
topic Computation and Language
H.2.5; I.2.7
url https://arxiv.org/abs/2603.10547