mlsanityData to 14 Oct 2026

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching

arXiv 2405.16884 ↗First posted 27 May 2024cs.CL cs.DBcited by 32

Not on the map. Why?

Abstract (arXiv)

Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary matching paradigm that ignores the global consistency among record relationships. In this paper, we investigate various methodologies for LLM-based entity matching that incorporate record interactions from different perspectives. Specifically, we comprehensively compare three representative strategies: matching, comparing, and selecting, and analyze their respective advantages and challenges in diverse scenarios. Based on our findings, we further design a compound entity matching framework (ComEM) that leverages the composition of multiple strategies and LLMs. ComEM benefits from the advantages of different sides and achieves improvements in both effectiveness and efficiency. Experimental results on 8 ER datasets and 10 LLMs verify the superiority of incorporating record interactions through the selecting strategy, as well as the further cost-effectiveness brought by ComEM.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 15 of its 48 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

15 of 48 references.

References · 15

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2017Graph Attention Networkscited by 8,923
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  6. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  7. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  8. 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
  9. 2020Deep Entity Matching with Pre-Trained Language Modelscited by 144
  10. 2020Neural Networks for Entity Matching: A Surveycited by 33
  11. 2019ZeroER: Entity Resolution using Zero Labeled Examplescited by 28
  12. 2020(Almost) All of Entity Resolutioncited by 23
3 more
  1. 2022Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparationcited by 19
  2. 2023WDC Products: A Multi-Dimensional Entity Matching Benchmarkcited by 17
  3. 2023A Critical Re-evaluation of Benchmark Datasets for (Deep) Learning-Based Matching Algorithmscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 21.

32 papers.

Sort:

By area:

  1. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  2. 2025LLM-empowered knowledge graph construction: A surveycited by 21
  3. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  4. 2025What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extractioncited by 6
  5. 2026LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptationcited by 6
  6. 2025Empowering Tabular Data Preparation with Language Models: Why and How?cited by 4
  7. 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Explorationcited by 3
  8. 2026Automatic End-to-End Data Integration using Large Language Modelscited by 3
  9. 2026PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?cited by 3
  10. 2025Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detectioncited by 2
  11. 2026Evaluation on Entity Matching in Recommender Systemscited by 2
  12. 2025TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistencycited by 1
20 more
  1. 2026Unlocking the Power of Large Language Models for Multi-table Entity Matchingcited by 1
  2. 2026Entity Resolution via Batched Oracle Queriescited by 1
  3. 2026Labeling Training Data for Entity Matching Using Large Language Modelscited by 1
  4. 2026MaDI-Bench: An End-to-End Data Integration Benchmarkcited by 1
  5. 2026CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMscited by 1
  6. 2025Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approachcited by 0
  7. 2025Beyond Traditional Algorithms: Leveraging LLMs for Accurate Cross-Border Entity Identificationcited by 0
  8. 2025Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolutioncited by 0
  9. 2025Bin2Vec: Interpretable and Auditable Multi-View Binary Analysis for Code Plagiarism Detectioncited by 0
  10. 2025EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detectioncited by 0
  11. 2026OpenSanctions Pairs: Large-Scale Entity Matching with LLMscited by 0
  12. 2026Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generationcited by 0
  13. 2026Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrievalcited by 0
  14. 2026Managing Map Cardinality in Automatic Disease Classification Mapping: Balancing Precision, Recall and Coveragecited by 0
  15. 2026Beyond Scale and Generation: Understanding Language Model-based Entity Matchingcited by 0
  16. 2026When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotatorscited by 0
  17. 2026BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligencecited by 0
  18. 2026KnowVis: Knowledge-Centric Visual Summarization for Video Lecturescited by 0
  19. 2026Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judgescited by 0
  20. 2026Billiger.de Products: A Bilingual Entity Matching Benchmarkcited by 0