# Learning from Natural Language Explanations for Generalizable Entity Matching

arXiv: https://arxiv.org/abs/2406.09330 · HTML: https://mlsanity.com/paper/2406.09330/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [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)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [DeepER -- Deep Entity Resolution](https://mlsanity.com/paper/1710.00597/) (2017)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [MISGENDERED: Limits of Large Language Models in Understanding Pronouns](https://mlsanity.com/paper/2306.03950/) (2023)
- [Low-resource Deep Entity Resolution with Transfer and Active Learning](https://mlsanity.com/paper/1906.08042/) (2019)
- [Efficient Domain Adaptation of Language Models via Adaptive Tokenization](https://mlsanity.com/paper/2109.07460/) (2021)
- [Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation](https://mlsanity.com/paper/2207.04122/) (2022)
- [Modeling Voting for System Combination in Machine Translation](https://mlsanity.com/paper/2007.06943/) (2020)
- [Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]](https://mlsanity.com/paper/2304.12329/) (2023)
- [DAME: Domain Adaptation for Matching Entities](https://mlsanity.com/paper/2204.09244/) (2022)
- [FlexER: Flexible Entity Resolution for Multiple Intents](https://mlsanity.com/paper/2209.07569/) (2022)
- [Neural Locality Sensitive Hashing for Entity Blocking](https://mlsanity.com/paper/2401.18064/) (2024)

## Built on by (most cited first, 6 of 6)

- [AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark](https://mlsanity.com/paper/2412.06724/) (2024)
- [Fine-tuning Large Language Models for Entity Matching](https://mlsanity.com/paper/2409.08185/) (2024)
- [Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing](https://mlsanity.com/paper/2502.18448/) (2025)
- [Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering](https://mlsanity.com/paper/2509.15403/) (2025)
- [Labeling Training Data for Entity Matching Using Large Language Models](https://mlsanity.com/paper/2606.28823/) (2026)
- [Entity Resolution in Practice: Lessons from a Self-Serve Pipeline](https://mlsanity.com/paper/2607.26298/) (2026)

## Abstract (arXiv)

Entity matching is the task of linking records from different sources that refer to the same real-world entity. Past work has primarily treated entity linking as a standard supervised learning problem. However, supervised entity matching models often do not generalize well to new data, and collecting exhaustive labeled training data is often cost prohibitive. Further, recent efforts have adopted LLMs for this task in few/zero-shot settings, exploiting their general knowledge. But LLMs are prohibitively expensive for performing inference at scale for real-world entity matching tasks. As an efficient alternative, we re-cast entity matching as a conditional generation task as opposed to binary classification. This enables us to "distill" LLM reasoning into smaller entity matching models via natural language explanations. This approach achieves strong performance, especially on out-of-domain generalization tests (10.85% F-1) where standalone generative methods struggle. We perform ablations that highlight the importance of explanations, both for performance and model robustness.