With the rapid advancement of large language models (LLMs), growing efforts have been made on LLM-based table retrieval. However, existing studies typically focus on single-table query, and implement it by similarity matching after encoding the entire table. These methods usually result in low accuracy due to their coarse-grained encoding which incorporates much query-irrelated data, and are also inefficient when dealing with large tables, failing to fully utilize the reasoning capabilities of LLM. Further, multi-table query is under-explored in retrieval tasks. To this end, we propose a hierarchical multi-table query method based on LLM: Fine-Grained Multi-Table Retrieval FGTR, a new retrieval paradigm that employs a human-like reasoning strategy. Through hierarchical reasoning, FGTR first identifies relevant schema elements and then retrieves the corresponding cell contents, ultimately constructing a concise and accurate sub-table that aligns with the given query. To comprehensively evaluate the performance of FGTR, we construct two new benchmark datasets based on Spider and BIRD . Experimental results show that FGTR outperforms previous state-of-the-art methods, improving the F_2 metric by 18% on Spider and 21% on BIRD, demonstrating its effectiveness in enhancing fine-grained retrieval and its potential to improve end-to-end performance on table-based downstream tasks.

翻译：随着大语言模型（LLM）的快速发展，基于LLM的表格检索研究日益增多。然而，现有研究通常聚焦于单表查询，并通过编码整个表格后进行相似度匹配来实现。这些方法由于采用粗粒度编码而引入了大量与查询无关的数据，通常导致准确率较低，且在处理大型表格时效率低下，未能充分利用LLM的推理能力。此外，多表查询在检索任务中尚未得到充分探索。为此，我们提出一种基于LLM的分层多表查询方法：细粒度多表检索FGTR，这是一种采用类人推理策略的新型检索范式。通过分层推理，FGTR首先识别相关的模式元素，然后检索对应的单元格内容，最终构建一个与给定查询对齐的简洁且准确的子表。为了全面评估FGTR的性能，我们基于Spider和BIRD构建了两个新的基准数据集。实验结果表明，FGTR优于以往最先进的方法，在Spider上将F_2指标提升了18%，在BIRD上提升了21%，证明了其在增强细粒度检索方面的有效性，以及在提升基于表格的下游任务端到端性能方面的潜力。