Large Language Models for Knowledge Graph Embedding Techniques, Methods, and Challenges: A Survey

2025-01-14

AI Summary

Existing research on integrating large language models (LLMs) with knowledge graph embedding (KGE) lacks a unified conceptual framework, hindering systematic comparison and adoption. Method: We propose the first task-oriented taxonomy for the LLM-KGE intersection, categorizing approaches by application paradigms—including multimodal KGE and open-domain KGE—and specifying model adaptation strategies for each. Through comprehensive literature analysis and methodological abstraction, we construct a structured survey table covering mainstream techniques, their application scenarios, technical characteristics, and publicly available implementations. We further introduce an extensible evaluation benchmark grounded in standardized metrics and datasets. Contribution/Results: This work provides a theoretically grounded, empirically informed foundation for LLM-KGE integration, delivering a practical guidance framework, reproducible resources, and concrete directions for future research—thereby advancing both methodological rigor and real-world applicability in neuro-symbolic AI.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large Language Models (LLMs) have attracted a lot of attention in various fields due to their superior performance, aiming to train hundreds of millions or more parameters on large amounts of text data to understand and generate natural language. As the superior performance of LLMs becomes apparent, they are increasingly being applied to knowledge graph embedding (KGE) related tasks to improve the processing results. As a deep learning model in the field of Natural Language Processing (NLP), it learns a large amount of textual data to predict the next word or generate content related to a given text. However, LLMs have recently been invoked to varying degrees in different types of KGE related scenarios such as multi-modal KGE and open KGE according to their task characteristics. In this paper, we investigate a wide range of approaches for performing LLMs-related tasks in different types of KGE scenarios. To better compare the various approaches, we summarize each KGE scenario in a classification. In addition to the categorization methods, we provide a tabular overview of the methods and their source code links for a more direct comparison. In the article we also discuss the applications in which the methods are mainly used and suggest several forward-looking directions for the development of this new research area.

Problem

• Large Language Models
• Knowledge Graph Embeddings
• Enhancement Techniques

Innovation

• Large Language Models
• Knowledge Graph Embeddings
• Multimodal and Open Scenarios