Constructing Knowledge Graphs from Text Using Large Language Models: Scoping Review

The use of Large Language Models (LLMs) for Knowledge Graph (KG) construction has gained significant traction, yet the field lacks methodological standardization. This study conducts a scope review following the PRISMA framework to map existing techniques and categorize them into four main approaches: (i) RDF-Based; (ii) Prompt-Based; (iii) RAG-Based; (iv) Hybrid Pipelines. Analyzing 126 primary studies, we identify key benefits such as scalability and automation, alongside challenges like low precision and manual curation. Our findings highlight research art-state.