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

Chuangtao Ma, Zeyu Zhang, Arijit Khan, Sebastian Schelter, Paul Groth
2/5/2026
cs.DBcs.CL

No official code found. Best implementation: machuangtao/CE-RAG4EM (3 stars, MIT, last commit 2026-04-20).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

machuangtao/CE-RAG4EMCommunity64%
MIT

CE-RAG4EM: Cost-efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration

30PythonJan 31, 20266 months agoMIT
data-integrationentity-matchingkg-ragrag

Similar Papers

RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving

87% match2025

Toward Optimal Search and Retrieval for RAG

85% match2024

CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation

84% match2024

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

84% match2 repos552024

Is Agentic RAG worth it? An experimental comparison of RAG approaches

84% match2026

Efficient Federated Search for Retrieval-Augmented Generation

84% match2025

Cite this paper

@article{ma2026costefficient,
  title  = {Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration},
  author = {Chuangtao Ma and Zeyu Zhang and Arijit Khan and Sebastian Schelter and Paul Groth},
  year   = {2026},
  eprint = {2602.05708},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2602.05708v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2602.05708.svg)](https://codeofpaper.com/paper/2602.05708)

Discussion