实体关系图(ERD) 是概念数据库设计的核心,，但它们通常仅作为渲染图像提供，而不是机器可读的模式,，限制了人工智能辅助数据库工程。我们推出了 EUnderstand,，这是第一个用于结构化理解 ER 图, 的大规模基准，其中包含从精选教育来源收集的 2,960 个图表, 现实世界模式, 以及跨不同领域的综合生成示例, 符号, 复杂性级别, 和扩展实体关系(EER) 构造。每个图表都配有标准化的机器可读表示形式，用于对模式元素进行细粒度评估。评估最先进的视觉语言模型 (VLMs), 我们发现，虽然常见的 ERD 元素可以可靠地恢复 (F1 > 0.74), 弱实体上的性能急剧下降 ( 低至 0.28 F1), 多值属性 (0.14 F1), 和 N 元关系(0.07 F1)。推理增强模型将整体性能提高了 15-25%，但对语言先验和不断增加的图表复杂性仍然敏感。 ERUnderstand 提供了一个标准化基准，用于评估概念数据库模式的多模式理解。基准,数据集,评估工具包,和生成代码可在此https URL上公开获得。
Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only as rendered images rather than machine-readable schemas, limiting AI-assisted database engineering. We introduce ERUnderstand, the first large-scale benchmark for structured understanding of ER diagrams, comprising 2,960 diagrams collected from curated educational sources, real-world schemas, and synthetically generated examples spanning diverse domains, notations, complexity levels, and Extended Entity-Relationship (EER) constructs. Each diagram is paired with a standardized machine-readable representation for fine-grained evaluation of schema elements. Evaluating state-of-the-art Vision-Language Models (VLMs), we find that while common ERD elements are recovered reliably (F1 > 0.74), performance drops sharply on weak entities (as low as 0.28 F1), multivalued attributes (0.14 F1), and N-ary relationships (0.07 F1). Reasoning-augmented models improve overall performance by 15-25% but remain sensitive to linguistic priors and increasing diagram complexity. ERUnderstand provides a standardized benchmark for evaluating multimodal understanding of conceptual database schemas. The benchmark, dataset, evaluation toolkit, and generation code are publicly available at this https URL.
科目: 人工智能 (cs.AI); 计算机视觉和模式识别 (cs.CV); 数据库 (cs.DB)
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Databases (cs.DB)