CLAIAug 20, 2024

GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models

arXiv:2408.10819v229 citationsh-index: 3
Originality Incremental advance
AI Analysis

This addresses the problem of incomplete knowledge graphs for applications relying on structured data, offering an incremental improvement by incorporating subgraph context into LLM-based methods.

The paper tackles knowledge graph completion by proposing GS-KGC, a framework that uses subgraph information with large language models to generate missing triples, resulting in a 5.6% increase in Hits@3 on FB15k-237N and a 9.3% increase on ICEWS14 compared to prior LLM-based methods.

Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are proposed for KGC task. However, most of them focus on prompt engineering while overlooking the fact that finer-grained subgraph information can aid LLMs in generating more accurate answers. In this paper, we propose a novel completion framework called \textbf{G}enerative \textbf{S}ubgraph-based KGC (GS-KGC), which utilizes subgraph information as contextual reasoning and employs a QA approach to achieve the KGC task. This framework primarily includes a subgraph partitioning algorithm designed to generate negatives and neighbors. Specifically, negatives can encourage LLMs to generate a broader range of answers, while neighbors provide additional contextual insights for LLM reasoning. Furthermore, we found that GS-KGC can discover potential triples within the KGs and new facts beyond the KGs. Experiments conducted on four common KGC datasets highlight the advantages of the proposed GS-KGC, e.g., it shows a 5.6\% increase in Hits@3 compared to the LLM-based model CP-KGC on the FB15k-237N, and a 9.3\% increase over the LLM-based model TECHS on the ICEWS14.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes