# Deep Entity Matching with Pre-Trained Language Models

arXiv: https://arxiv.org/abs/2004.00584 · HTML: https://mlsanity.com/paper/2004.00584/

## Key facts

- Cited by 144 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 30 of 144)

- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [Annotating Columns with Pre-trained Language Models](https://mlsanity.com/paper/2104.01785/) (2021)
- [OLaLa: Ontology Matching with Large Language Models](https://mlsanity.com/paper/2311.03837/) (2023)
- [Large Language Models as Data Preprocessors](https://mlsanity.com/paper/2308.16361/) (2023)
- [Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching](https://mlsanity.com/paper/2405.16884/) (2024)
- [Entity Matching using Large Language Models](https://mlsanity.com/paper/2310.11244/) (2023)
- [Supervised Contrastive Learning for Product Matching](https://mlsanity.com/paper/2202.02098/) (2022)
- [AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark](https://mlsanity.com/paper/2412.06724/) (2024)
- [Using ChatGPT for Entity Matching](https://mlsanity.com/paper/2305.03423/) (2023)
- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [The Design of an LLM-powered Unstructured Analytics System](https://mlsanity.com/paper/2409.00847/) (2024)
- [WDC Products: A Multi-Dimensional Entity Matching Benchmark](https://mlsanity.com/paper/2301.09521/) (2023)
- [VerifAI: Verified Generative AI](https://mlsanity.com/paper/2307.02796/) (2023)
- [ReMatch: Retrieval Enhanced Schema Matching with LLMs](https://mlsanity.com/paper/2403.01567/) (2024)
- [Fine-tuning Large Language Models for Entity Matching](https://mlsanity.com/paper/2409.08185/) (2024)
- [DeepJoin: Joinable Table Discovery with Pre-trained Language Models](https://mlsanity.com/paper/2212.07588/) (2022)
- [Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration](https://mlsanity.com/paper/2312.03987/) (2023)
- [OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining](https://mlsanity.com/paper/2402.15810/) (2024)
- [MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.05587/) (2025)
- [Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]](https://mlsanity.com/paper/2304.12329/) (2023)
- [Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models](https://mlsanity.com/paper/2306.05052/) (2023)
- [Construction of Knowledge Graphs: State and Challenges](https://mlsanity.com/paper/2302.11509/) (2023)
- [Observatory: Characterizing Embeddings of Relational Tables](https://mlsanity.com/paper/2310.07736/) (2023)
- [CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models](https://mlsanity.com/paper/2304.10946/) (2023)
- [DP-TabICL: In-Context Learning with Differentially Private Tabular Data](https://mlsanity.com/paper/2403.05681/) (2024)
- [Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction](https://mlsanity.com/paper/2205.05889/) (2022)
- [e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce](https://mlsanity.com/paper/2207.00208/) (2022)
- [LakeBench: Benchmarks for Data Discovery over Data Lakes](https://mlsanity.com/paper/2307.04217/) (2023)

## Abstract (arXiv)

We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architecture. Our experiments show that a straightforward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets. We also developed three optimization techniques to further improve Ditto's matching capability. Ditto allows domain knowledge to be injected by highlighting important pieces of input information that may be of interest when making matching decisions. Ditto also summarizes strings that are too long so that only the essential information is retained and used for EM. Finally, Ditto adapts a SOTA technique on data augmentation for text to EM to augment the training data with (difficult) examples. This way, Ditto is forced to learn "harder" to improve the model's matching capability. The optimizations we developed further boost the performance of Ditto by up to 9.8%. Perhaps more surprisingly, we establish that Ditto can achieve the previous SOTA results with at most half the number of labeled data. Finally, we demonstrate Ditto's effectiveness on a real-world large-scale EM task. On matching two company datasets consisting of 789K and 412K records, Ditto achieves a high F1 score of 96.5%.