arXiv cs.CL· Chuangtao Ma, Zeyu Zhang, Arijit Khan, Sebastian Schelter, Paul Groth·· 2 天前AI 评分22
CE-RAG4EM：面向 LLM 实体匹配的成本高效 RAG 分块批处理框架
Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing Framework
AI 导读
研究者提出 CE-RAG4EM 框架，通过基于分块的批量检索与生成，降低 LLM 实体匹配中 RAG 的端到端开销。在九个真实实体匹配基准数据集上，该框架在零样本设置下取得相当或更优的匹配质量，并在属性模糊或数值稀疏的数据集上显著提升 F1 分数。分析还揭示了分块批量大小与检索粒度上的性能-开销权衡。
正文 · 原文
Abstract:Large language models (LLMs) offer a compelling approach to entity matching (EM) in label-scarce settings, yet their matching quality is sensitive to records with ambiguous or sparse attributes due to the absence of external factual grounding. Retrieval-augmented generation (RAG) directly addresses this grounding gap by retrieving and injecting relevant external knowledge. However, naively applying RAG to large-scale EM is expensive due to per-pair retrieval calls over large knowledge graphs (KGs) and the increase in input tokens caused by enriching prompts with retrieved contextual knowledge. To address the above limitation, we introduce a CE-RAG4EM (Cost-Efficient RAG for Entity Matching) framework that reduces overhead through blocking-based batch retrieval and generation. We investigate the benefits of this framework through a systematic analysis of RAG systems for entity matching, focusing on blocking-aware batch optimizations and retrieval granularity. Extensive experiments on nine widely used real-world entity matching benchmark datasets show that CE-RAG4EM under a zero-shot setting achieves comparable or improved matching quality while substantially reducing end-to-end overhead. The results demonstrate that our CE-RAG4EM closes the knowledge grounding gap of the LLM-EM baseline and yields significant improvements in F1 scores on datasets with ambiguous or numerically sparse attributes, while its batch retrieval and inference substantially reduce the overhead and maintain competitive matching quality compared to naive RAG4EM. Our analysis identifies clear performance-overhead trade-offs across blocking-based batch sizes and retrieval granularity, showing how matching quality and computational cost shift with each design choice. These findings offer concrete guidance for building scalable, efficient RAG systems for entity matching that balance accuracy and cost.
| Comments: | Extended version of the paper accepted at ACM SIGMOD 2027 |
| Subjects: | Databases (cs.DB); Computation and Language (cs.CL) |
| Cite as: | arXiv:2602.05708 [cs.DB] |
| (or arXiv:2602.05708v2 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2602.05708 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3856323
DOI(s) linking to related resources |
Submission history
From: Chuangtao Ma [view email]
[v1]
Thu, 5 Feb 2026 14:33:00 UTC (536 KB)
[v2]
Thu, 15 Oct 2026 13:36:53 UTC (626 KB)
来源：arXiv cs.CL · arxiv.org