让机器从杂乱文本中精准提取数据，错误率从30%降到1%以下。
Relational Deep Dive: Error-Aware Queries Over Unstructured Data
- 动态发现查询专属的表格结构，自动对齐跨文档信息。
- 通过轻量级分类器和统计校准，将错误率压至1%以下。
- 适合需要高准确性的金融、医疗等关键领域数据分析。
非结构化数据广泛存在，但分析查询需要结构化表示，导致提取难题。现有方法如RAG缺乏模式感知能力，难以实现跨文档对齐，错误率较高。我们提出ReDD（Relational Deep Dive）框架，可动态发现查询相关的模式，填充关系表，并提供可证明的误差保障。ReDD采用两阶段流程：(1) 迭代模式发现（ISD）识别最小且可连接的查询特定模式；(2) 表格数据填充（TDP）利用基于LLM隐状态训练的轻量级分类器进行数据提取与纠错。主要贡献包括SCAPE——一种具有覆盖率保证的统计校准误差检测方法，以及SCAPE-HYB——在准确率与人工修正成本间取得优化平衡的混合方法。在多个数据集上的实验表明，ReDD将数据提取错误率从最高30%降至低于1%，同时保持100%召回率和高精度。模块化设计支持对准确率-成本权衡的细粒度控制，适用于高风险分析场景中的非结构化语料处理。
原文摘要 · Abstract (English)
Unstructured data is pervasive, but analytical queries demand structured representations, creating a significant extraction challenge. Existing methods like RAG lack schema awareness and struggle with cross-document alignment, leading to high error rates. We propose ReDD (Relational Deep Dive), a framework that dynamically discovers query-specific schemas, populates relational tables, and ensures error-aware extraction with provable guarantees. ReDD features a two-stage pipeline: (1) Iterative Schema Discovery (ISD) identifies minimal, joinable schemas tailored to each query, and (2) Tabular Data Population (TDP) extracts and corrects data using lightweight classifiers trained on LLM hidden states. A main contribution of ReDD is SCAPE, a statistically calibrated method for error detection with coverage guarantees, and SCAPE-HYB, a hybrid approach that optimizes the trade-off between accuracy and human correction costs. Experiments across diverse datasets demonstrate ReDD's effectiveness, reducing data extraction errors from up to 30% to below 1% while maintaining high schema completeness (100% recall) and precision. ReDD's modular design enables fine-grained control over accuracy-cost trade-offs, making it a robust solution for high-stakes analytical queries over unstructured corpora.
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。