Leveraging Large Language Models for Generating Research Topic Ontologies: A Multi-Disciplinary Study
arXiv:2508.20693v2 Announce Type: replace-cross Abstract: Ontologies and taxonomies of research fields are critical for managing and organising scientific knowledge, as they facilitate efficient classification, dissemination and retrieval of information. However, the creation and maintenance of such ontologies are expensive and time-consuming tasks, usually requiring the coordinated effort of multiple domain experts. Consequently, ontologies in this space often exhibit uneven coverage across different disciplines, limited inter-discipline connectivity, and infrequent updating cycles. In this s
The rapid advancement and increased capabilities of Large Language Models (LLMs) have made them suitable for complex knowledge organization tasks, a development observed frequently in 2024-2025.
This study demonstrates how LLMs can automate the critical and labor-intensive process of creating and maintaining research ontologies, significantly accelerating scientific knowledge organization and dissemination.
The method of building and updating comprehensive, interdisciplinary taxonomies for scientific research can become largely automated and more dynamic, moving away from slow, manual expert-driven processes.
- · Academic researchers
- · Scientific publishers
- · Knowledge management platforms
- · AI developers
- · Manual ontology developers
- · Traditional information gatekeepers
More efficient and interconnected knowledge bases will emerge across scientific disciplines.
Accelerated cross-disciplinary research and discovery due to improved access and organization of information.
The potential for AI to autonomously generate and curate entire fields of knowledge, fundamentally altering the nature of scientific inquiry and education.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL