# Schema Matching with Large Language Models: an Experimental Study

arXiv: https://arxiv.org/abs/2407.11852 · HTML: https://mlsanity.com/paper/2407.11852/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 6 of 6)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Valentine: Evaluating Matching Techniques for Dataset Discovery](https://mlsanity.com/paper/2010.07386/) (2020)
- [A Semi-Automated Hybrid Schema Matching Framework for Vegetation Data Integration](https://mlsanity.com/paper/2305.06528/) (2023)

## Built on by (most cited first, 20 of 20)

- [Magneto: Combining Small and Large Language Models for Schema Matching](https://mlsanity.com/paper/2412.08194/) (2024)
- [A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs](https://mlsanity.com/paper/2504.14657/) (2025)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs](https://mlsanity.com/paper/2410.12480/) (2024)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [Towards Scalable Schema Mapping using Large Language Models](https://mlsanity.com/paper/2505.24716/) (2025)
- [Transduction is All You Need for Structured Data Workflows](https://mlsanity.com/paper/2508.15610/) (2025)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs](https://mlsanity.com/paper/2511.18364/) (2025)
- [Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection](https://mlsanity.com/paper/2512.07246/) (2025)
- [High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services](https://mlsanity.com/paper/2504.17203/) (2025)
- [Machine Learning for Detection and Analysis of Novel LLM Jailbreaks](https://mlsanity.com/paper/2510.01644/) (2025)
- [Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates](https://mlsanity.com/paper/2510.14900/) (2025)
- [Can AI autonomously build, operate, and use the entire data stack?](https://mlsanity.com/paper/2512.07926/) (2025)
- [SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability](https://mlsanity.com/paper/2603.28731/) (2026)
- [By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode](https://mlsanity.com/paper/2605.25186/) (2026)
- [Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case](https://mlsanity.com/paper/2608.26750/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling](https://mlsanity.com/paper/2610.00907/) (2026)
- [Label Agreement Does Not Measure Authorization](https://mlsanity.com/paper/2610.04544/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown useful applications in a variety of tasks, including data wrangling. In this paper, we investigate the use of an off-the-shelf LLM for schema matching. Our objective is to identify semantic correspondences between elements of two relational schemas using only names and descriptions. Using a newly created benchmark from the health domain, we propose different so-called task scopes. These are methods for prompting the LLM to do schema matching, which vary in the amount of context information contained in the prompt. Using these task scopes we compare LLM-based schema matching against a string similarity baseline, investigating matching quality, verification effort, decisiveness, and complementarity of the approaches. We find that matching quality suffers from a lack of context information, but also from providing too much context information. In general, using newer LLM versions increases decisiveness. We identify task scopes that have acceptable verification effort and succeed in identifying a significant number of true semantic matches. Our study shows that LLMs have potential in bootstrapping the schema matching process and are able to assist data engineers in speeding up this task solely based on schema element names and descriptions without the need for data instances.