{"ID":2893262,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14376","arxiv_id":"2507.14376","title":"Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms","abstract":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling efficient identification of candidate matches without relying on labeled training data or exhaustive pairwise comparisons. By enriching schema metadata and leveraging both vector-based and lexical retrieval, SCHEMORA improves matching accuracy and scalability. Evaluated on the MIMIC-OMOP benchmark, it establishes new state-of-the-art performance, with gains of 7.49% in HitRate@5 and 3.75% in HitRate@3 over previous best results. To our knowledge, this is the first LLM-based schema matching method with an open-source implementation, accompanied by analysis that underscores the critical role of retrieval and provides practical guidance on model selection.","short_abstract":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling e...","url_abs":"https://arxiv.org/abs/2507.14376","url_pdf":"https://arxiv.org/pdf/2507.14376v1","authors":"[\"Osman Erman Gungor\",\"Derak Paulsen\",\"William Kang\"]","published":"2025-07-18T21:50:36Z","proceeding":"cs.DB","tasks":"[\"cs.DB\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}