The State of the Art LLMs for Knowledge Graph Construction from Text
KGC 2025
•
2h 47m
Nandana Mihindukulasooriya, IBM Research, Senior Research Scientist
Jennifer D`Souza, TIB Leibniz Information Centre for Science and Technology, Hannover, Germany, Postdoctoral Researcher
Knowledge graphs (KGs) play a crucial role in modern applications. However, automatically constructing a KG from natural language text is challenging due to the complexities of natural languages. This tutorial will focus on the state-of-the-art LLM-based methods, techniques, and tools for constructing knowledge graphs from text, discussing their capabilities, limitations, and current challenges. During the last year, emerging topics such as Retrieval Augmented Generation (RAG), GraphRAG, Chain-of-Thought, LLM Agents, and reasoning models have driven the development of numerous new entity and relation extraction methods that are helpful for KG generation from text.
Our aim is to summarize the research progress in KG construction from text, with a specific focus on the information acquisition branch that includes entity and relation extraction, covering state-of-the-art transformer methods and tools. Our session will explore the theoretical foundations of innovative approaches while also providing practical, hands-on exercises for deeper understanding. This overview will be valuable for both practitioners engaged in building organizational knowledge graphs and academics interested in the cutting edge of research.
Up Next in KGC 2025
-
Creating High-Quality Knowledge Graph...
Prashanth Rao, Kùzu, Inc, AI Engineer
Paco Nathan, Senzing, Principal DevRel EngineerAn important obstacle for adopting knowledge graph technology in enterprises is that virtually all of the enterprise-level data is originally stored in unstructured formats or in some structured but non-graph f...
-
The Ultimate Guide to Knowledge-Based AI
Valerio Cocchi, Oxford Semantic Technologies, Lead Knowledge Engineer
Knowledge-based AI has been launched into the mainstream as it serves as the antidote to LLM hallucinations in RAG systems—an increasingly visible feature but just one of many critical applications in which Knowledge-based AI ...
-
AI-Assisted Knowledge Graph Extractio...
Dean Allemang, data.world, principal solution architect
Knowledge Graphs are integral components in enterprise data management and foundational elements of reliable AI-based systems. But the question remains - how do we construct a knowledge base and populate it with our information?
For sever...
