NeurOWL · Jul 17, 2026
NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
A paper titled 'NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning' was published on arXiv on 2026-07-17. It proposes an end-to-end neuro-symbolic framework that jointly performs verification and abduction for incomplete OWL ontologies, leveraging Large Language Models and ontology embeddings. The framework addresses subsumption reasoning without requiring a predefined candidate set of missing axioms. Evaluation on real-world ontologies across multiple domains shows strong and robust performance.
What happened
NeurOWL is a neuro-symbolic framework that combines Large Language Models with ontology embeddings to perform subsumption verification and abduction on incomplete OWL ontologies. It determines whether a non-entailed subsumption is semantically plausible and provides logically sound explanations with potential missing axioms. The framework was evaluated on real-world ontologies from multiple domains, demonstrating robust performance.
Technical significance
NeurOWL integrates formal OWL semantics with the textual semantics captured by LLMs and ontology embeddings, enabling joint verification and abduction without a predefined axiom candidate set. This approach generalizes ontology abduction and could improve reasoning over incomplete knowledge bases.
Industry impact
The framework targets domains like healthcare and bioinformatics where ontologies are often incomplete. By automating the identification of plausible missing axioms, it could reduce manual ontology curation efforts and enhance semantic reasoning in knowledge-intensive applications.
What to watch
Future signals may include open-source release of the NeurOWL code, integration with existing ontology editors, or application to specific biomedical ontologies. Further research could explore scaling to larger ontologies or combining with other neuro-symbolic methods.
Decision value
NeurOWL could lower the cost of maintaining and extending ontologies in industries that rely on formal knowledge representation, potentially enabling more accurate decision support systems in healthcare, life sciences, and semantic web applications.