Abstract

The growing need to integrate information from many diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex and costly to maintain. While recent advances suggest that large language models (LLMs) can assist in automating schema mapping, key challenges remain. We motivate future research in schema mapping generation by highlighting key challenges, presenting a competitive bidirectional schema matching pipeline, and exploring the limitations of current methods for generating more complex mappings.

Citation

Christopher Buss, Mahdis Safari, Arash Termehchy, Stefan Lee, and David Maier. 2025. ”Towards Scalable Schema Mapping using Large Language Models”, SIGMOD Workshop on Modern Integrated Database and AI Systems (MIDAS), June 2025.

@article{buss2025towards,
  title={Towards Scalable Schema Mapping using Large Language Models},
  author={Buss, Christopher and Safari, Mahdis and Termehchy, Arash and Lee, Stefan and Maier, David},
  journal={arXiv preprint arXiv:2505.24716},
  year={2025}
}