In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration

TL;DR

This paper introduces a novel in-context clustering method using Large Language Models for Entity Resolution, significantly improving accuracy and efficiency while reducing costs compared to traditional pairwise approaches.

Contribution

It proposes LLM-CER, a scalable clustering-based ER approach that explores the design space and addresses challenges like cluster merging and hallucination, advancing LLM applications in ER.

Findings

Up to 150% higher accuracy in ER tasks.

10% increase in F-measure over baselines.

API calls reduced by up to 5 times.

Abstract

Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly in terms of time and monetary resources, especially with large datasets. Recently, Large Language Models (LLMs) have shown promising results in ER tasks. However, existing methods typically focus on pairwise matching, missing the potential of LLMs to perform clustering directly in a more cost-effective and scalable manner. In this paper, we propose a novel in-context clustering approach for ER, where LLMs are used to cluster records directly, reducing both time complexity and monetary costs. We systematically investigate the design space for in-context clustering, analyzing the impact of factors such as set size, diversity, variation, and ordering of records on clustering performance. Based on these insights, we develop LLM-CER (LLM-powered Clustering-based ER), which achieves high-quality ER results while minimizing LLM API calls. Our approach addresses key challenges, including efficient cluster merging and LLM hallucination, providing a scalable and effective solution for ER. Extensive experiments on nine real-world datasets demonstrate that our method significantly improves result quality, achieving up to 150% higher accuracy, 10% increase in the F-measure, and reducing API calls by up to 5 times, while maintaining comparable monetary cost to the most cost-effective baseline.