动态精简大复杂度数据模式，提升大模型结构化信息抽取效率
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
- 基于模式元数据和少量示例，动态裁剪输出模式空间
- 在医疗与电商数据上实现8.8%的微平均F1提升，延迟降低47%
- 适合需要高效处理复杂数据模式的工业级应用
使用大语言模型从非结构化文本中提取结构化数据，在目标模式较大且复杂时面临挑战。此时将完整模式加入提示会增加成本和延迟，导致性能下降，并可能超出上下文长度限制。我们提出SchemaRAG，一种检索增强生成框架，通过利用模式元数据和可用的少量示例，动态裁剪面向模式的信息抽取任务中的输出模式空间。我们在真实世界的医疗和电商数据集上评估了SchemaRAG。结果表明，SchemaRAG可实现最高8.8%的微平均F1提升，延迟降低47%，令牌成本减少48%，证明其在大规模模式抽取中的实用性。
原文摘要 · Abstract (English)
Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples when available. We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.
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。