.png){kind=icon}
.png){kind=icon}
Return
GS-KGC: A generative subgraph-based framework for knowledge graph completion with large language models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2024.102868.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 G enerative S ubgraph-based KGC (GSKGC), 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 GSKGC 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.
Keywords:
Knowledge graph
Knowledge graph completion
Large language models
Question answer