EasyEA: Large Language Model is All You Need in Entity Alignment Between Knowledge Graphs

ACL ARR 2025 February Submission7493 Authors

Abstract: Entity alignment (EA) aims to identify entities in different knowledge graphs (KGs) that represent the same real-world objects. Traditional EA methods typically embed entity information into vector space under the guidance of seed entity pairs, and align entities by calculating and comparing the similarity between entity embeddings. With the advent of large language models (LLMs), emerging methods are increasingly integrating LLMs with traditional methods to leverage external knowledge and improve EA accuracy. However, this integration also introduces additional computational complexity and operational overhead, and still requires seed pairs that are scarce and expensive to obtain. To address these challenges, we propose EasyEA, the first end-to-end EA framework based on LLMs that requires no training. EasyEA consists of three main stages: (1) Information Summarization, (2) Embedding and Feature Fusion, and (3) Candidate Selection. By automating the EA process, EasyEA significantly reduces the reliance on seed entity pairs while demonstrating superior performance across various datasets, covering Cross-lingual, sparse, large-scale, and heterogeneous scenarios. Extensive experimental results show that EasyEA not only simplifies the EA process but also achieves state-of-the-art (SOTA) performance on diverse datasets, providing a promising solution for advancing EA tasks.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Knowledge Graphs, Entity Alignment, LLMs

Contribution Types: Model analysis & interpretability, Theory

Languages Studied: English, Chinese, France, Japanese

Submission Number: 7493