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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Rui, Zhu, Jiahao, Man, Jianping, Liu, Hongze, Fang, Li, Zhou, Yi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913633710112768
author Yang, Rui
Zhu, Jiahao
Man, Jianping
Liu, Hongze
Fang, Li
Zhou, Yi
author_facet Yang, Rui
Zhu, Jiahao
Man, Jianping
Liu, Hongze
Fang, Li
Zhou, Yi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10819
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models
Yang, Rui
Zhu, Jiahao
Man, Jianping
Liu, Hongze
Fang, Li
Zhou, Yi
Computation and Language
Artificial Intelligence
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.
title GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.10819