基于分块策略的LLM实体匹配成本优化研究：RAG方法探索

摘要

检索增强生成技术虽能提升大语言模型在知识密集型任务中的推理能力，但现有RAG流程应用于大规模实体匹配时存在显著的检索与生成开销。为突破此局限，我们提出CE-RAG4EM——一种基于分块批处理检索与生成的高效RAG架构。同时建立统一分析框架，重点从分块感知优化和检索粒度两个维度评估实体匹配中的RAG系统。大量实验表明，相较于强基线模型，CE-RAG4EM在保持相当或更优匹配质量的同时，能显著降低端到端运行时间。进一步分析揭示，关键配置参数在性能与开销间存在固有权衡，这为设计高效可扩展的实体匹配及数据集成RAG系统提供了实践指导。

English

Retrieval-augmented generation (RAG) enhances LLM reasoning in knowledge-intensive tasks, but existing RAG pipelines incur substantial retrieval and generation overhead when applied to large-scale entity matching. To address this limitation, we introduce CE-RAG4EM, a cost-efficient RAG architecture that reduces computation through blocking-based batch retrieval and generation. We also present a unified framework for analyzing and evaluating RAG systems for entity matching, focusing on blocking-aware optimizations and retrieval granularity. Extensive experiments suggest that CE-RAG4EM can achieve comparable or improved matching quality while substantially reducing end-to-end runtime relative to strong baselines. Our analysis further reveals that key configuration parameters introduce an inherent trade-off between performance and overhead, offering practical guidance for designing efficient and scalable RAG systems for entity matching and data integration.

基于分块策略的LLM实体匹配成本优化研究：RAG方法探索

Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration

摘要

Support