用大模型生成表说明，高效选出可关联的多表解决文本转SQL难题
CORE-T: COherent REtrieval of Tables for Text-to-SQL
- 给每张表加大模型生成的用途标签，预计算表间兼容性
- 比纯向量检索提升22.7分表选择准确率，多表执行准确率高24.4分
- 无需训练、推理快，适合大规模异构数据库场景
真实文本转SQL任务常需关联多张表，但在无数据库标识等清晰线索的大规模异构表集合中，精准召回相关表成为关键瓶颈。现有密集检索（DR）虽召回率高，但含大量干扰项；而依赖额外假设或高推理开销的联接感知方法效果有限。本文提出CORE-T，一种无需训练、可扩展的框架：通过大模型为表添加用途元数据，并预计算轻量级表兼容性缓存。推理时，先用DR获取前K个候选表，再通过一次大模型调用筛选出语义连贯且可联接的子集，最后经两阶段增量调整恢复强兼容表。在Bird、Spider、MMQA和Beaver数据集上，相较DR，CORE-T在表选择F1上最高提升22.7分，返回表数减少最多40%，多表执行准确率最高提升24.4分，总选择令牌消耗仅为基线的1.64-4.20倍。
原文摘要 · Abstract (English)
Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be answered over large, heterogeneous table collections pooled from many sources, without clean scoping signals such as database identifiers. Here, dense retrieval (DR) achieves high recall but returns many distractors, while join-aware alternatives often rely on extra assumptions and/or incur high inference overhead. We propose CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache. At inference time, DR returns top-K candidates; a single LLM call selects a coherent, joinable subset, and a two-step additive adjustment stage restores strongly compatible tables. Across Bird, Spider, MMQA, and Beaver, CORE-T improves over DR by up to 22.7 points in table-selection F1 while returning up to 40% fewer tables, and by up to 24.4 points in multi-table execution accuracy, and uses 1.64-4.20x fewer total selection tokens than LLM-intensive baselines.
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。