Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Combining Knowledge Graphs and Large Language Models

Amanda Kau, Xuzeng He, Aishwarya Nambissan, Aland Astudillo, Hui Yin, Amir Aryani

TL;DR

This survey addresses the problem of LLMs exhibiting hallucinations and knowledge gaps by examining how Knowledge Graphs (KGs) can ground and enhance LLM capabilities. It surveys 28 papers, categorizing approaches into KG-empowered LLMs, LLM-empowered KGs, and hybrid methods, and provides a taxonomy distinguishing Add-ons from Joint architectures. Key contributions include a thematic analysis, a synthesis of methodologies (knowledge injection, graph-based reasoning, KG construction, and forecasting with Temporal Knowledge Graphs), and a critical discussion of strengths and limitations such as domain coverage, computational costs, and knowledge update challenges. The work informs researchers and practitioners about practical pathways to building more trustworthy, interpretable, and domain-aware AI systems by integrating KGs with LLMs, and points to open issues in knowledge integration, efficiency, and multimodal extensions.

Abstract

In recent years, Natural Language Processing (NLP) has played a significant role in various Artificial Intelligence (AI) applications such as chatbots, text generation, and language translation. The emergence of large language models (LLMs) has greatly improved the performance of these applications, showing astonishing results in language understanding and generation. However, they still show some disadvantages, such as hallucinations and lack of domain-specific knowledge, that affect their performance in real-world tasks. These issues can be effectively mitigated by incorporating knowledge graphs (KGs), which organise information in structured formats that capture relationships between entities in a versatile and interpretable fashion. Likewise, the construction and validation of KGs present challenges that LLMs can help resolve. The complementary relationship between LLMs and KGs has led to a trend that combines these technologies to achieve trustworthy results. This work collected 28 papers outlining methods for KG-powered LLMs, LLM-based KGs, and LLM-KG hybrid approaches. We systematically analysed and compared these approaches to provide a comprehensive overview highlighting key trends, innovative techniques, and common challenges. This synthesis will benefit researchers new to the field and those seeking to deepen their understanding of how KGs and LLMs can be effectively combined to enhance AI applications capabilities.

Combining Knowledge Graphs and Large Language Models

TL;DR

This survey addresses the problem of LLMs exhibiting hallucinations and knowledge gaps by examining how Knowledge Graphs (KGs) can ground and enhance LLM capabilities. It surveys 28 papers, categorizing approaches into KG-empowered LLMs, LLM-empowered KGs, and hybrid methods, and provides a taxonomy distinguishing Add-ons from Joint architectures. Key contributions include a thematic analysis, a synthesis of methodologies (knowledge injection, graph-based reasoning, KG construction, and forecasting with Temporal Knowledge Graphs), and a critical discussion of strengths and limitations such as domain coverage, computational costs, and knowledge update challenges. The work informs researchers and practitioners about practical pathways to building more trustworthy, interpretable, and domain-aware AI systems by integrating KGs with LLMs, and points to open issues in knowledge integration, efficiency, and multimodal extensions.

Abstract

In recent years, Natural Language Processing (NLP) has played a significant role in various Artificial Intelligence (AI) applications such as chatbots, text generation, and language translation. The emergence of large language models (LLMs) has greatly improved the performance of these applications, showing astonishing results in language understanding and generation. However, they still show some disadvantages, such as hallucinations and lack of domain-specific knowledge, that affect their performance in real-world tasks. These issues can be effectively mitigated by incorporating knowledge graphs (KGs), which organise information in structured formats that capture relationships between entities in a versatile and interpretable fashion. Likewise, the construction and validation of KGs present challenges that LLMs can help resolve. The complementary relationship between LLMs and KGs has led to a trend that combines these technologies to achieve trustworthy results. This work collected 28 papers outlining methods for KG-powered LLMs, LLM-based KGs, and LLM-KG hybrid approaches. We systematically analysed and compared these approaches to provide a comprehensive overview highlighting key trends, innovative techniques, and common challenges. This synthesis will benefit researchers new to the field and those seeking to deepen their understanding of how KGs and LLMs can be effectively combined to enhance AI applications capabilities.
Paper Structure (10 sections, 2 equations, 4 figures)

This paper contains 10 sections, 2 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Background
  3. Large Language Models (LLMs)
  4. Knowledge Graphs (KGs)
  5. LLMs Empowered by KGs
  6. KGs Empowered by LLMs
  7. Hybrid Approaches
  8. Thematic Analysis
  9. Strengths and Limitations of Existing Research
  10. Conclusion

Figures (4)

  • Figure 1: LLM text generation workflow.
  • Figure 2: KG-enhancement for LLMs can come in the form of (i) KG knowledge injection into LLM prompts or (ii) other methods where KGs directly contribute to LLMs.
  • Figure 3: LLM-enhanced KG construction, where (i) LLMs are used for information extraction or (ii) for general KG data operations.
  • Figure 4: Hybrid Approaches that combine text and KG embeddings.