# Entity Matching using Large Language Models

arXiv: https://arxiv.org/abs/2310.11244 · HTML: https://mlsanity.com/paper/2310.11244/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [DeepER -- Deep Entity Resolution](https://mlsanity.com/paper/1710.00597/) (2017)
- [Neural Networks for Entity Matching: A Survey](https://mlsanity.com/paper/2010.11075/) (2020)
- [Supervised Contrastive Learning for Product Matching](https://mlsanity.com/paper/2202.02098/) (2022)
- [Using ChatGPT for Entity Matching](https://mlsanity.com/paper/2305.03423/) (2023)
- [Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation](https://mlsanity.com/paper/2207.04122/) (2022)
- [WDC Products: A Multi-Dimensional Entity Matching Benchmark](https://mlsanity.com/paper/2301.09521/) (2023)
- [Machamp: A Generalized Entity Matching Benchmark](https://mlsanity.com/paper/2106.08455/) (2021)
- [Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]](https://mlsanity.com/paper/2304.12329/) (2023)
- [PromptEM: Prompt-tuning for Low-resource Generalized Entity Matching](https://mlsanity.com/paper/2207.04802/) (2022)
- [DAME: Domain Adaptation for Matching Entities](https://mlsanity.com/paper/2204.09244/) (2022)
- [Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution](https://mlsanity.com/paper/2310.06174/) (2023)
- [CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration](https://mlsanity.com/paper/2108.08090/) (2021)

## Built on by (most cited first, 30 of 31)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [Fine-tuning Large Language Models for Entity Matching](https://mlsanity.com/paper/2409.08185/) (2024)
- [Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration](https://mlsanity.com/paper/2312.03987/) (2023)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Generalizable and Scalable Multistage Biomedical Concept Normalization Leveraging Large Language Models](https://mlsanity.com/paper/2405.15122/) (2024)
- [Automatic End-to-End Data Integration using Large Language Models](https://mlsanity.com/paper/2603.10547/) (2026)
- [CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies](https://mlsanity.com/paper/2505.04365/) (2025)
- [Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications](https://mlsanity.com/paper/2505.14918/) (2025)
- [3dSAGER: Geospatial Entity Resolution over 3D Objects (Technical Report)](https://mlsanity.com/paper/2511.06300/) (2025)
- [EnsembleLink: Accurate Record Linkage Without Training Data](https://mlsanity.com/paper/2601.21138/) (2026)
- [Entity Resolution via Batched Oracle Queries](https://mlsanity.com/paper/2606.24407/) (2026)
- [MaDI-Bench: An End-to-End Data Integration Benchmark](https://mlsanity.com/paper/2606.30371/) (2026)
- [Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach](https://mlsanity.com/paper/2502.10453/) (2025)
- [Leveraging Language Models for Automated Patient Record Linkage](https://mlsanity.com/paper/2504.15261/) (2025)
- [Beyond Traditional Algorithms: Leveraging LLMs for Accurate Cross-Border Entity Identification](https://mlsanity.com/paper/2507.11086/) (2025)
- [Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings](https://mlsanity.com/paper/2509.15858/) (2025)
- [Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation](https://mlsanity.com/paper/2510.14271/) (2025)
- [OpenSanctions Pairs: Large-Scale Entity Matching with LLMs](https://mlsanity.com/paper/2603.11051/) (2026)
- [SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability](https://mlsanity.com/paper/2603.28731/) (2026)
- [Attribution Markets: A Fisher-Market Formulation for Fractional Credit Assignment Between Planned Tasks and Performed Actions](https://mlsanity.com/paper/2607.20694/) (2026)
- [Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAG](https://mlsanity.com/paper/2607.22319/) (2026)
- [Leveraging Semantic Maps for City-Scale Cross-View Localization](https://mlsanity.com/paper/2607.25215/) (2026)
- [Entity Resolution in Practice: Lessons from a Self-Serve Pipeline](https://mlsanity.com/paper/2607.26298/) (2026)
- [Constraint-Guided Enterprise Data Mapping with Large Language Models](https://mlsanity.com/paper/2608.24218/) (2026)
- [MERGED: Multimodal Entity Resolution via Generated Expert Reasoning Distillation](https://mlsanity.com/paper/2609.01913/) (2026)
- [Corporate-Family Resolution Is Not a String-Matching Problem: A Public Benchmark Stratified by Name Visibility](https://mlsanity.com/paper/2609.04269/) (2026)
- [Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges](https://mlsanity.com/paper/2609.33878/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)
- [Follow the Entities: A Corpus Map for Agentic Search](https://mlsanity.com/paper/2609.37226/) (2026)

## Abstract (arXiv)

Entity matching is the task of deciding whether two entity descriptions refer to the same real-world entity. Entity matching is a central step in most data integration pipelines. Many state-of-the-art entity matching methods rely on pre-trained language models (PLMs) such as BERT or RoBERTa. Two major drawbacks of these models for entity matching are that (i) the models require significant amounts of task-specific training data and (ii) the fine-tuned models are not robust concerning out-of-distribution entities. This paper investigates using generative large language models (LLMs) as a less task-specific training data-dependent and more robust alternative to PLM-based matchers. The study covers hosted and open-source LLMs which can be run locally. We evaluate these models in a zero-shot scenario and a scenario where task-specific training data is available. We compare different prompt designs and the prompt sensitivity of the models. We show that there is no single best prompt but that the prompt needs to be tuned for each model/dataset combination. We further investigate (i) the selection of in-context demonstrations, (ii) the generation of matching rules, as well as (iii) fine-tuning LLMs using the same pool of training data. Our experiments show that the best LLMs require no or only a few training examples to perform comparably to PLMs that were fine-tuned using thousands of examples. LLM-based matchers further exhibit higher robustness to unseen entities. We show that GPT4 can generate structured explanations for matching decisions and can automatically identify potential causes of matching errors by analyzing explanations of wrong decisions. We demonstrate that the model can generate meaningful textual descriptions of the identified error classes, which can help data engineers to improve entity matching pipelines.