Efficient Visualization of Knowledge Graphs Based on Next-Generation Language Models

From Unstructured Procedural Text to Knowledge Graphs: Comparing LLM-Based Extraction Strategies

As experienced workers retire across industrialized economies, organizations risk losing procedural expertise that often remains tacit, undocumented or scattered across unstructured documents. Translating this knowledge into structured, machine-readable representations is difficult to scale, labor-intensive, and prone to inconsistency when done manually. This paper addresses the automated construction of knowledge graphs from natural language procedural descriptions, developing a generic approach for transforming unstructured expert knowledge into structured knowledge graphs that support downstream retrieval and question-answering applications. Three text-to-knowledge-graph approaches were designed, implemented, and systematically evaluated. The first employed a large general-purpose language model (Qwen3-32B) with a single-stage zero-shot extraction prompt, the second applied the same strategy using a smaller base model (Llama2-13B), and the third combined supervised fine-tuning of the smaller model on synthetic extraction data with a decomposed extraction architecture targeting one to two ontology elements per phase. All approaches were evaluated across six procedural descriptions spanning multiple technical domains, with chunk size, model temperature, and ontology detail as configuration parameters. Results were assessed for intrinsic quality and extrinsic fitness for use, measured by question-answering accuracy in a Graph-RAG application. The results demonstrate that extraction strategy is a more decisive factor than model capacity. The fine-tuned model achieved a Question Answering (QA) pass rate of 55.3%, compared to 46.8% for the large model and 33% for the small base model, outperforming the general-purpose model on both intrinsic quality metrics and downstream performance. Average node degree, duplication rate, and ontology simplicity emerge as the strongest predictors of retrieval performance. Shorter ontologies consistently outperformed richer ones, suggesting that ontology design should be driven by the intended downstream application rather than semantic completeness. Over-extraction of procedural steps did not degrade performance but instead improved retrieval robustness by providing additional entry points for graph traversal. The findings offer practical guidance for designing scalable, locally deployable knowledge graph construction pipelines for procedural texts under computational and confidentiality constraints.

An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents

A production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology, and improved search recall from roughly 70 to 95 percent with no false merges, and corrected seven classes of silent quality defect.

Information modeling of scientific articles for semantic publishing: theory, models and applications

The digital proliferation of scientific articles since the 1980s has made strategic reading an essential skill for researchers. To support automatic filtering, linking and analysis of scientific literature, fine-grained scientific content, extensive semantic links and machine-readable formats are required. This review aims to analyze and compare existing models of scientific articles for semantic publishing and to provide future directions for their development. The review followed the PRISMA 2020 guidelines and systematically searched two major databases (WoS and Scopus). A total of 159 articles were screened and synthesized, and key studies were selectively cited to support the narrative review. We synthesized 34 existing models, the theories they employ, and the applications of these models, resulting in 3 theoretical perspectives, 4 types of modeling content and 4 types of applications. The review categorizes model content into four orthogonal aspects based on the granularity of textual units: bibliographic records, textual structure, discourse structure and entity types and relationships. The review reveals three main theoretical perspectives on modeling: the scientific paper as an instance of a text model, the scientific paper as a genre of scientific discourse and the scientific paper as an argumentation of scientific claims. Different types of information models are found to serve distinct purposes. This review provides direction for the automated processing and analysis of scientific papers and reference for the modeling of other types of scientific documents.

Exploiting Mapping Corpora and Expert Knowledge for LLM-based Schema Mapping Generation

Archival Knowledge Graphs: Balancing Semantic Richness and Accessibility of Hierarchical Structures

Formal Concept Analysis for Topic Modeling and Visualization