LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs

TL;DR

This paper proposes a Large Language Model (LLM) based Entity Alignment method, LLM-Align, which explores the instruction-following and zero-shot capabilities of Large Language Models to infer alignments of entities.

Abstract

Entity Alignment (EA) seeks to identify and match corresponding entities across different Knowledge Graphs (KGs), playing a crucial role in knowledge fusion and integration. Embedding-based entity alignment (EA) has recently gained considerable attention, resulting in the emergence of many innovative approaches. Initially, these approaches concentrated on learning entity embeddings based on the structural features of knowledge graphs (KGs) as defined by relation triples. Subsequent methods have integrated entities' names and attributes as supplementary information to improve the embeddings used for EA. However, existing methods lack a deep semantic understanding of entity attributes and relations. In this paper, we propose a Large Language Model (LLM) based Entity Alignment method, LLM-Align, which explores the instruction-following and zero-shot capabilities of Large Language Models to infer alignments of entities. LLM-Align uses heuristic methods to select important attributes and relations of entities, and then feeds the selected triples of entities to an LLM to infer the alignment results. To guarantee the quality of alignment results, we design a multi-round voting mechanism to mitigate the hallucination and positional bias issues that occur with LLMs. Experiments on three EA datasets, demonstrating that our approach achieves state-of-the-art performance compared to existing EA methods.

Figures (6)

• Figure 1: The framework of LLM-Align.
• Figure 2: Prompts for LLM-Align.
• Figure 3: Experimental Results Affected by Positional Bias.
• Figure 4: Impact of Model Scale on EA Reasoning.
• Figure 5: Impact of Model Scale on EA for high-difficulty entity and low-difficulty entity