LLMs like GPT-4 used to build ontologies for Blue Amazon domain

Researchers have explored the use of Large Language Models (LLMs) like GPT-3.5 and GPT-4 to automate the construction of domain-specific ontologies, a task typically requiring significant manual effort. Experiments focused on the Brazilian maritime territory, known as the Blue Amazon, resulted in twenty ontologies generated by the LLMs. While these models produced generally coherent conceptualizations, human expert evaluation indicated that none of the automatically generated ontologies were fully satisfactory without further refinement. AI

IMPACT LLM-driven ontology generation could accelerate knowledge organization in specialized fields, though human oversight remains crucial for accuracy.

RANK_REASON The cluster contains an academic paper detailing research on applying LLMs to ontology construction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Blue Amazon
• GPT-3.5
• GPT-4
• Large Language Models
• Vivian Magri Alcaldi Soares

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →