Structured Multi-Step Reasoning for Entity Matching Using Large Language Model
Rohan Bopardikar, Jin Wang, Jia Zou
TL;DR
This work addresses entity matching by introducing structured multi-step reasoning in prompts for large language models. It proposes a three-step framework that first identifies token-level matches, then assesses attribute-level importance, and finally makes an entity-level decision, optionally augmented by a debate-based reasoning phase. Across six real-world benchmarks, reasoning-based prompting yields consistent accuracy gains in several settings while incurring higher prompt costs, highlighting a promising yet cost-sensitive direction for reasoning-guided EM. The study underscores the potential for interpretable and robust EM through explicit intermediate reasoning signals and outlines avenues for improving efficiency and reliability.
Abstract
Entity matching is a fundamental task in data cleaning and data integration. With the rapid adoption of large language models (LLMs), recent studies have explored zero-shot and few-shot prompting to improve entity matching accuracy. However, most existing approaches rely on single-step prompting and offer limited investigation into structured reasoning strategies. In this work, we investigate how to enhance LLM-based entity matching by decomposing the matching process into multiple explicit reasoning stages. We propose a three-step framework that first identifies matched and unmatched tokens between two records, then determines the attributes most influential to the matching decision, and finally predicts whether the records refer to the same real-world entity. In addition, we explore a debate-based strategy that contrasts supporting and opposing arguments to improve decision robustness. We evaluate our approaches against multiple existing baselines on several real-world entity matching benchmark datasets. Experimental results demonstrate that structured multi-step reasoning can improve matching performance in several cases, while also highlighting remaining challenges and opportunities for further refinement of reasoning-guided LLM approaches.