用大模型生成查询，让表格搜索更准。
PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
- 构建表格画像+大模型生成伪查询，实现内容驱动的搜索
- 在元数据缺失场景下，检索准确率显著超越传统方法
- 适合缺乏完整元数据的开放数据集搜索场景
数据湖、数据空间和开放数据门户中表格数据快速增长，高效的数据集搜索对复用与分析至关重要。现有系统主要依赖元数据，但常不完整或质量低，尤其当表格语义依赖模式与单元格值时。近期大语言模型（LLMs）可生成更丰富的表格内容表示。然而，已有基于LLM的检索方法多聚焦于表格问答任务，即为问题选择单个相关表格，而非检索并排序相关数据集。本文提出PIPER，一种面向表格数据集的内容驱动检索方法，结合表格画像与大模型生成的伪查询，进行稠密向量检索。该方法专为元数据贫瘠场景设计，在多个基准上优于经典元数据基线和强表问答检索方法，验证了基于大模型的内容建模在表格数据集搜索中的价值。
原文摘要 · Abstract (English)
The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis. Existing search systems rely mainly on metadata, which is often incomplete or low quality, especially for tables whose meaning depends on both schema and cell values. Recent advances in Large Language Models (LLMs) enable richer, content-based representations of tables. However, prior LLM-based retrieval methods have focused on Table Question Answering, where the goal is to select a single table to answer a question, rather than retrieve and rank relevant datasets. We propose PIPER, a content-driven retrieval method for tabular datasets that uses table profiles and LLM-generated queries embedded for dense retrieval. Designed for dataset search in poor-metadata settings, PIPER outperforms both classical metadata-based baselines and strong TableQA retrieval methods, demonstrating the value of LLM-based content modeling for tabular dataset search.
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。