# AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model

arXiv: https://arxiv.org/abs/2409.04073 · HTML: https://mlsanity.com/paper/2409.04073/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Distributed Inference and Fine-tuning of Large Language Models Over The Internet](https://mlsanity.com/paper/2312.08361/) (2023)
- [A Declarative System for Optimizing AI Workloads](https://mlsanity.com/paper/2405.14696/) (2024)
- [ZeroER: Entity Resolution using Zero Labeled Examples](https://mlsanity.com/paper/1908.06049/) (2019)
- [Production Machine Learning Pipelines: Empirical Analysis and Optimization Opportunities](https://mlsanity.com/paper/2103.16007/) (2021)
- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [Modeling Voting for System Combination in Machine Translation](https://mlsanity.com/paper/2007.06943/) (2020)
- [DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching](https://mlsanity.com/paper/2301.02993/) (2023)
- [REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines](https://mlsanity.com/paper/2302.04702/) (2023)
- [Machop: an End-to-End Generalized Entity Matching Framework](https://mlsanity.com/paper/2206.04853/) (2022)
- [Navigating the Data Lake with Datamaran: Automatically Extracting Structure from Log Datasets](https://mlsanity.com/paper/1708.08905/) (2017)
- [Gen-T: Table Reclamation in Data Lakes](https://mlsanity.com/paper/2403.14128/) (2024)

## Built on by (most cited first, 5 of 5)

- [Fine-tuning Large Language Models for Entity Matching](https://mlsanity.com/paper/2409.08185/) (2024)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration](https://mlsanity.com/paper/2602.05708/) (2026)
- [Beyond Traditional Algorithms: Leveraging LLMs for Accurate Cross-Border Entity Identification](https://mlsanity.com/paper/2507.11086/) (2025)
- [OpenSanctions Pairs: Large-Scale Entity Matching with LLMs](https://mlsanity.com/paper/2603.11051/) (2026)

## Abstract (arXiv)

Entity matching (EM) is the problem of determining whether two records refer to same real-world entity, which is crucial in data integration, e.g., for product catalogs or address databases. A major drawback of many EM approaches is their dependence on labelled examples. We thus focus on the challenging setting of zero-shot entity matching where no labelled examples are available for an unseen target dataset. Recently, large language models (LLMs) have shown promising results for zero-shot EM, but their low throughput and high deployment cost limit their applicability and scalability. We revisit the zero-shot EM problem with AnyMatch, a small language model fine-tuned in a transfer learning setup. We propose several novel data selection techniques to generate fine-tuning data for our model, e.g., by selecting difficult pairs to match via an AutoML filter, by generating additional attribute-level examples, and by controlling label imbalance in the data. We conduct an extensive evaluation of the prediction quality and deployment cost of our model, in a comparison to thirteen baselines on nine benchmark datasets. We find that AnyMatch provides competitive prediction quality despite its small parameter size: it achieves the second-highest F1 score overall, and outperforms several other approaches that employ models with hundreds of billions of parameters. Furthermore, our approach exhibits major cost benefits: the average prediction quality of AnyMatch is within 4.4% of the state-of-the-art method MatchGPT with the proprietary trillion-parameter model GPT-4, yet AnyMatch requires four orders of magnitude less parameters and incurs a 3,899 times lower inference cost (in dollars per 1,000 tokens).