用大模型解析查询中的结构化条件，提升表格数据检索精度。
HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
- 用大模型提取自然语言中的属性约束，作为过滤条件
- 结合嵌入搜索处理剩余语义内容，显著提升召回率
- 适合需要混合结构与语义查询的推荐系统场景
真实推荐系统中的用户查询常同时包含结构化约束（如类别、属性）和非结构化偏好（如商品描述或评论）。我们提出HyST（半结构化表格数据上的混合检索框架），将大模型驱动的结构化过滤与基于嵌入的语义搜索相结合，支持对半结构化表格数据的复杂信息需求。HyST利用大语言模型从自然语言中提取属性级约束，并将其作为元数据过滤器；同时通过嵌入检索处理查询中未结构化的部分。在半结构化基准测试上，HyST持续优于传统基线方法，凸显了结构化过滤对提升检索精度的重要性，为真实用户查询提供了可扩展且精准的解决方案。
原文摘要 · Abstract (English)
User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over Semi-structured Tabular data), a hybrid retrieval framework that combines LLM-powered structured filtering with semantic embedding search to support complex information needs over semi-structured tabular data. HyST extracts attribute-level constraints from natural language using large language models (LLMs) and applies them as metadata filters, while processing the remaining unstructured query components via embedding-based retrieval. Experiments on a semi-structured benchmark show that HyST consistently outperforms tradtional baselines, highlighting the importance of structured filtering in improving retrieval precision, offering a scalable and accurate solution for real-world user queries.
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。