Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.05708 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911424474775552 |
|---|---|
| author | Ma, Chuangtao Zhang, Zeyu Khan, Arijit Schelter, Sebastian Groth, Paul |
| author_facet | Ma, Chuangtao Zhang, Zeyu Khan, Arijit Schelter, Sebastian Groth, Paul |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05708 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration Ma, Chuangtao Zhang, Zeyu Khan, Arijit Schelter, Sebastian Groth, Paul Databases Computation and Language 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. |
| title | Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration |
| topic | Databases Computation and Language |
| url | https://arxiv.org/abs/2602.05708 |