用大模型+检索提升数据模式匹配效率，无需标注数据。
Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms
- 结合大模型与混合检索，通过提示工程识别候选匹配。
- 在MIMIC-OMOP上达新基准，HitRate@5提升7.49%。
- 首个开源LLM模式匹配方案，适合数据集成与发现场景。
模式匹配对整合异构数据源和提升数据集发现至关重要，但仍是复杂且资源密集的问题。我们提出SCHEMORA，一个融合大语言模型与混合检索技术的提示驱动框架，可在不依赖标注数据或全量配对的情况下高效识别候选匹配。通过丰富模式元数据并结合向量与词法检索，SCHEMORA提升了匹配准确率与可扩展性。在MIMIC-OMOP基准上评估，其在HitRate@5上相比先前最佳结果提升7.49%，在HitRate@3上提升3.75%。据我们所知，这是首个具有开源实现的基于LLM的模式匹配方法，并附有分析，强调了检索机制的关键作用，为模型选择提供实用指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。