# From Subsumption to Satisfiability: LLM-Assisted Active Learning for OWL Ontologies

arXiv: https://arxiv.org/abs/2604.16672 · HTML: https://mlsanity.com/paper/2604.16672/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 42 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [Language Model Analysis for Ontology Subsumption Inference](https://mlsanity.com/paper/2302.06761/) (2023)
- [Exact Learning of Lightweight Description Logic Ontologies](https://mlsanity.com/paper/1709.07314/) (2017)
- [Actively Learning Concepts and Conjunctive Queries under ELr-Ontologies](https://mlsanity.com/paper/2105.08326/) (2021)
- [Large Language Model for OWL Proofs](https://mlsanity.com/paper/2601.12444/) (2026)

## Built on by (most cited first, 1 of 1)

- [NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning](https://mlsanity.com/paper/2607.15776/) (2026)

## Abstract (arXiv)

In active learning, membership queries (MQs) allow a learner to pose questions to a teacher, such as ''Is every apple a fruit?'', to which the teacher responds correctly with yes or no. These MQs can be viewed as subsumption tests with respect to the target ontology. Inspired by the standard reduction of subsumption to satisfiability in description logics, we reformulate each candidate axiom into its corresponding counter-concept and verbalise it in controlled natural language before presenting it to Large Language Models (LLMs). We introduce LLMs as a third component that provides real-world examples approximating an instance of the counter-concept. This design property ensures that only Type II errors may occur in ontology modelling; in the worst case, these errors merely delay the construction process without introducing inconsistencies. Experimental results on 13 commercial LLMs show that recall, corresponding to Type II errors in our framework, remains stable across several well-established ontologies.