Unlocking the Power of Large Language Models for Entity Alignment

TL;DR

To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy.

Abstract

Entity Alignment (EA) is vital for integrating diverse knowledge graph (KG) data, playing a crucial role in data-driven AI applications. Traditional EA methods primarily rely on comparing entity embeddings, but their effectiveness is constrained by the limited input KG data and the capabilities of the representation learning techniques. Against this backdrop, we introduce ChatEA, an innovative framework that incorporates large language models (LLMs) to improve EA. To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy. To overcome the over-reliance on entity embedding comparisons, ChatEA implements a two-stage EA strategy that capitalizes on LLMs' capability for multi-step reasoning in a dialogue format, thereby enhancing accuracy while preserving efficiency. Our experimental results verify ChatEA's superior performance, highlighting LLMs' potential in facilitating EA tasks.

Figures (4)

• Figure 1: A comparison of previous EA and ChatEA.
• Figure 2: The overview framework of our proposed ChatEA, which consists of three main components: (1) entity feature pre-processing, (2) KG-code translation, and (3) two-stage EA strategy.
• Figure 3: Performance influence of entity embeddings comparing ChatEA and Simple-HHEA for EA.
• Figure 4: Proportions of iteration rounds of ChatEA's two-stage reasoning on different datasets.