LLMs and embedding models refine ontologies in casting domain case study

Researchers have developed a new method for refining ontologies, which are used to organize complex knowledge, by combining fine-tuned ontology embedding models with Large Language Models (LLMs). This approach was tested on CASTON, an ontology for the casting domain, where it successfully identified candidate axioms for refinement and provided repair suggestions. An expert evaluation showed that the system, utilizing a CASTON-fine-tuned OnT embedding model and the Qwen3-8B LLM, produced high-confidence repairs, with all six suggested replacements being accepted by domain experts. AI

IMPACT This research demonstrates a novel approach to improving knowledge representation using LLMs, potentially enhancing AI's ability to understand and organize complex domain-specific information.

RANK_REASON This is a research paper detailing a novel method for ontology refinement using LLMs and embeddings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Caston
• Large Language Models
• Ontology
• Qwen3_8B

• paper
• other

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