Automatic End-to-End Data Integration using Large Language Models
This work addresses the high manual effort and cost for data engineers in designing data integration pipelines, though it is incremental as it builds on existing LLM capabilities for individual steps.
The authors tackled the problem of automating end-to-end data integration pipelines by using GPT-5.2 to generate all necessary artifacts, such as schema mappings and training data, and found that the LLM-based pipeline produced results comparable to or better than human-designed pipelines in case studies involving video game, music, and company data, with costs of approximately $10 per case study.
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.