REaR提升多表检索质量，不依赖大模型却效果媲美顶尖系统。
REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval
- 分三阶段：先找相关表，再扩增可连接的表，最后剔除噪声表。
- 在BIRD、MMQA、Spider上提升检索与SQL生成效果，精度更高且延迟更低。
- 无需大模型，适合对效率和成本敏感的表格问答场景。
自然语言查询关系数据常需跨多表检索与推理，但现有检索器仅优化查询-表相关性，忽视表间结构兼容性。本文提出REaR（Retrieve, Expand and Refine）框架，分三阶段实现高效高保真多表检索：(i) 检索与查询匹配的表；(ii) 通过预计算的列嵌入快速比较，扩展出结构可连接的表；(iii) 通过剪枝去除噪声或弱相关候选。实验表明，REaR不依赖大模型，在复杂表问答数据集BIRD、MMQA和Spider上，显著提升密集/稀疏检索器的多表检索质量与下游SQL执行性能。尽管无LLM，其表现仍媲美前沿的LLM增强系统（如ARM），且延迟和成本大幅降低。消融实验验证了扩展与精炼的互补增益，证明REaR是表任务（如Text-to-SQL）中实用且可扩展的核心组件。
原文摘要 · Abstract (English)
Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table table compatibility. We introduce REAR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REAR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REAR is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g.,ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REAR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).
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。