Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-empowered knowledge graph construction: A survey

Haonan Bian

TL;DR

The survey analyzes how Large Language Models (LLMs) transform knowledge graph construction by unifying natural language and structured data across ontology engineering, knowledge extraction, and knowledge fusion. It categorizes approaches into schema-based and schema-free paradigms and further into top-down versus bottom-up ontology construction, static versus dynamic extraction, and schema-level versus instance-level fusion. Key contributions include a synthesis of representative frameworks (e.g., CQ-based ontology generation, Open Information Extraction, Extract-Define-Canonicalize, AutoSchemaKG, KARMA) and the identification of open challenges such as scalability, continual adaptation, and multimodal integration. The work highlights future directions in KG-based reasoning, dynamic memory for agentic systems, and multimodal KG construction to enable adaptive, explainable knowledge-centric AI systems.

Abstract

Knowledge Graphs (KGs) have long served as a fundamental infrastructure for structured knowledge representation and reasoning. With the advent of Large Language Models (LLMs), the construction of KGs has entered a new paradigm-shifting from rule-based and statistical pipelines to language-driven and generative frameworks. This survey provides a comprehensive overview of recent progress in LLM-empowered knowledge graph construction, systematically analyzing how LLMs reshape the classical three-layered pipeline of ontology engineering, knowledge extraction, and knowledge fusion. We first revisit traditional KG methodologies to establish conceptual foundations, and then review emerging LLM-driven approaches from two complementary perspectives: schema-based paradigms, which emphasize structure, normalization, and consistency; and schema-free paradigms, which highlight flexibility, adaptability, and open discovery. Across each stage, we synthesize representative frameworks, analyze their technical mechanisms, and identify their limitations. Finally, the survey outlines key trends and future research directions, including KG-based reasoning for LLMs, dynamic knowledge memory for agentic systems, and multimodal KG construction. Through this systematic review, we aim to clarify the evolving interplay between LLMs and knowledge graphs, bridging symbolic knowledge engineering and neural semantic understanding toward the development of adaptive, explainable, and intelligent knowledge systems.

LLM-empowered knowledge graph construction: A survey

TL;DR

The survey analyzes how Large Language Models (LLMs) transform knowledge graph construction by unifying natural language and structured data across ontology engineering, knowledge extraction, and knowledge fusion. It categorizes approaches into schema-based and schema-free paradigms and further into top-down versus bottom-up ontology construction, static versus dynamic extraction, and schema-level versus instance-level fusion. Key contributions include a synthesis of representative frameworks (e.g., CQ-based ontology generation, Open Information Extraction, Extract-Define-Canonicalize, AutoSchemaKG, KARMA) and the identification of open challenges such as scalability, continual adaptation, and multimodal integration. The work highlights future directions in KG-based reasoning, dynamic memory for agentic systems, and multimodal KG construction to enable adaptive, explainable knowledge-centric AI systems.

Abstract

Knowledge Graphs (KGs) have long served as a fundamental infrastructure for structured knowledge representation and reasoning. With the advent of Large Language Models (LLMs), the construction of KGs has entered a new paradigm-shifting from rule-based and statistical pipelines to language-driven and generative frameworks. This survey provides a comprehensive overview of recent progress in LLM-empowered knowledge graph construction, systematically analyzing how LLMs reshape the classical three-layered pipeline of ontology engineering, knowledge extraction, and knowledge fusion. We first revisit traditional KG methodologies to establish conceptual foundations, and then review emerging LLM-driven approaches from two complementary perspectives: schema-based paradigms, which emphasize structure, normalization, and consistency; and schema-free paradigms, which highlight flexibility, adaptability, and open discovery. Across each stage, we synthesize representative frameworks, analyze their technical mechanisms, and identify their limitations. Finally, the survey outlines key trends and future research directions, including KG-based reasoning for LLMs, dynamic knowledge memory for agentic systems, and multimodal KG construction. Through this systematic review, we aim to clarify the evolving interplay between LLMs and knowledge graphs, bridging symbolic knowledge engineering and neural semantic understanding toward the development of adaptive, explainable, and intelligent knowledge systems.
Paper Structure (27 sections, 1 figure)

This paper contains 27 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Ontology Engineering
  4. Knowledge Extraction
  5. Knowledge Fusion
  6. LLM-Enhanced Ontology Construction
  7. Top-down Ontology Construction: LLMs as Ontology Assistants
  8. Competency Question (CQ)-Based Ontology Construction
  9. Natural Language-Based Ontology Construction
  10. Bottom-up Ontology Schema Construction: KGs for LLMs
  11. LLM-Driven Knowledge Extraction
  12. Schema-Based Methods
  13. Static Schema-Driven Extraction
  14. Dynamic and Adaptive Schema-Based Extraction
  15. Schema-free Methods
  16. ...and 12 more sections

Figures (1)

  • Figure 1: Taxonomy of LLM for KGC