Matchmaker: Schema Matching with self-improving compositional LLM programs

Nabeel Seedat, Mihaela van der Schaar

Keywords: schema matching, data-centric AI, Large Language Models, healthcare

TL;DR: schema matching across heterogenous data sources using compositional language model programs

Abstract: Schema matching -- the task of finding matches between attributes across disparate data sources with different tables and hierarchies -- is critical for creating interoperable machine learning (ML)-ready data. Addressing this fundamental data-centric problem has wide implications, especially in domains like healthcare, finance and e-commerce --- but also has the potential to benefit ML models more generally, by increasing the data available for ML model training. However, schema matching is a challenging ML task due to structural/hierarchical and semantic heterogeneity between different schemas. Previous ML approaches to automate schema matching have either required significant labeled data for model training, which is often unrealistic, or suffer from poor zero-shot performance. To this end, we propose Matchmaker - a compositional language model program for schema matching, comprised of candidate generation, refinement and confidence scoring. Matchmaker also self-improves in a zero-shot manner without the need for labeled demonstrations via a novel optimization approach, which constructs synthetic in-context demonstrations to guide the language model's reasoning process. Empirically, we demonstrate on real-world medical schema matching benchmarks that Matchmaker outperforms previous ML-based approaches, highlighting its potential to accelerate data integration and interoperability of ML-ready data.

Primary Area: other topics in machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7911