MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation

Knowledge graph completion (KGC) is a critical task for addressing the incompleteness of knowledge graphs and supporting downstream applications. However, it faces significant challenges, including insufficient structured information and uneven entity distribution. Although existing methods have all...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengfei Yue, Hailiang Tang, Wanyu Li, Wenxiao Zhang, Bingjie Yan
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032146886950912
author Pengfei Yue
Hailiang Tang
Wanyu Li
Wenxiao Zhang
Bingjie Yan
author_facet Pengfei Yue
Hailiang Tang
Wanyu Li
Wenxiao Zhang
Bingjie Yan
author_sort Pengfei Yue
collection DOAJ
description Knowledge graph completion (KGC) is a critical task for addressing the incompleteness of knowledge graphs and supporting downstream applications. However, it faces significant challenges, including insufficient structured information and uneven entity distribution. Although existing methods have alleviated these issues to some extent, they often rely heavily on extensive training and fine-tuning, which results in low efficiency. To tackle these challenges, we introduce our MLKGC framework, a novel approach that combines large language models (LLMs) with multi-modal modules (MMs). LLMs leverage their advanced language understanding and reasoning abilities to enrich the contextual information for KGC, while MMs integrate multi-modal data, such as audio and images, to bridge knowledge gaps. This integration augments the capability of the model to address long-tail entities, enhances its reasoning processes, and facilitates more robust information integration through the incorporation of diverse inputs. By harnessing the synergy between LLMs and MMs, our approach reduces dependence on traditional text-based training and fine-tuning, providing a more efficient and accurate solution for KGC tasks. It also offers greater flexibility in addressing complex relationships and diverse entities. Extensive experiments on multiple benchmark KGC datasets demonstrate that MLKGC effectively leverages the strengths of both LLMs and multi-modal data, achieving superior performance in link-prediction tasks.
format Article
id doaj-art-e970d6ded3434387a62b3b3fab41a830
institution DOAJ
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-e970d6ded3434387a62b3b3fab41a8302025-08-20T02:58:44ZengMDPI AGMathematics2227-73902025-04-01139146310.3390/math13091463MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal AugmentationPengfei Yue0Hailiang Tang1Wanyu Li2Wenxiao Zhang3Bingjie Yan4School of Information Science and Engineering, Qilu Normal University, Jinan 250200, ChinaSchool of Information Science and Engineering, Qilu Normal University, Jinan 250200, ChinaSchool of Humanities, Arts, and Social Sciences, Kunsan National University, Gunsan 54150, Republic of KoreaSchool of Computer Science and Engineering, Kunsan National University, Gunsan 54150, Republic of KoreaSchool of Mathematics, High School Attached to Shandong Normal University, Jinan 250200, ChinaKnowledge graph completion (KGC) is a critical task for addressing the incompleteness of knowledge graphs and supporting downstream applications. However, it faces significant challenges, including insufficient structured information and uneven entity distribution. Although existing methods have alleviated these issues to some extent, they often rely heavily on extensive training and fine-tuning, which results in low efficiency. To tackle these challenges, we introduce our MLKGC framework, a novel approach that combines large language models (LLMs) with multi-modal modules (MMs). LLMs leverage their advanced language understanding and reasoning abilities to enrich the contextual information for KGC, while MMs integrate multi-modal data, such as audio and images, to bridge knowledge gaps. This integration augments the capability of the model to address long-tail entities, enhances its reasoning processes, and facilitates more robust information integration through the incorporation of diverse inputs. By harnessing the synergy between LLMs and MMs, our approach reduces dependence on traditional text-based training and fine-tuning, providing a more efficient and accurate solution for KGC tasks. It also offers greater flexibility in addressing complex relationships and diverse entities. Extensive experiments on multiple benchmark KGC datasets demonstrate that MLKGC effectively leverages the strengths of both LLMs and multi-modal data, achieving superior performance in link-prediction tasks.https://www.mdpi.com/2227-7390/13/9/1463large language modelsmulti-modal moduleknowledge graph completion
spellingShingle Pengfei Yue
Hailiang Tang
Wanyu Li
Wenxiao Zhang
Bingjie Yan
MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
Mathematics
large language models
multi-modal module
knowledge graph completion
title MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
title_full MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
title_fullStr MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
title_full_unstemmed MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
title_short MLKGC: Large Language Models for Knowledge Graph Completion Under Multimodal Augmentation
title_sort mlkgc large language models for knowledge graph completion under multimodal augmentation
topic large language models
multi-modal module
knowledge graph completion
url https://www.mdpi.com/2227-7390/13/9/1463
work_keys_str_mv AT pengfeiyue mlkgclargelanguagemodelsforknowledgegraphcompletionundermultimodalaugmentation
AT hailiangtang mlkgclargelanguagemodelsforknowledgegraphcompletionundermultimodalaugmentation
AT wanyuli mlkgclargelanguagemodelsforknowledgegraphcompletionundermultimodalaugmentation
AT wenxiaozhang mlkgclargelanguagemodelsforknowledgegraphcompletionundermultimodalaugmentation
AT bingjieyan mlkgclargelanguagemodelsforknowledgegraphcompletionundermultimodalaugmentation