Back to feed
arXiv cs.CL
arXiv cs.CL
6/23/2026
Specific Domain Ontology Construction Using Large Language Models

Specific Domain Ontology Construction Using Large Language Models

Short summary

Researchers used GPT-3.5 and GPT-4 to automatically construct domain ontologies for Brazil's maritime territory, finding coherent but incomplete conceptualizations requiring human refinement. The work demonstrates LLMs can bootstrap domain knowledge structures where reference ontologies don't exist. Results show promise but confirm human expert validation is essential for production use.

  • •GPT-3.5/4 successfully generated coherent domain ontologies for a specialized maritime domain
  • •All 20 outputs required human expert refinement before being satisfactory
  • •Useful technique for domains lacking reference ontologies but demands quality assurance

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools
Read full article at arXiv cs.CL

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models
arXiv CS.AI
Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study
arXiv CS.AI
Ontology in Computer Science and Artificial Intelligence: A Developer’s Practical Guide
Dev.to
How Wayfair Uses GPT-5.5 to Power Catalog Enrichment Across 40M Products
OpenAI