# NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning

arXiv: https://arxiv.org/abs/2607.15776 · HTML: https://mlsanity.com/paper/2607.15776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [OWL2Vec*: Embedding of OWL Ontologies](https://mlsanity.com/paper/2009.14654/) (2020)
- [EL Embeddings: Geometric construction of models for the Description Logic EL ++](https://mlsanity.com/paper/1902.10499/) (2019)
- [Contextual Semantic Embeddings for Ontology Subsumption Prediction](https://mlsanity.com/paper/2202.09791/) (2022)
- [Language Models as Hierarchy Encoders](https://mlsanity.com/paper/2401.11374/) (2024)
- [OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction](https://mlsanity.com/paper/1804.10922/) (2018)
- [Faithiful Embeddings for EL++ Knowledge Bases](https://mlsanity.com/paper/2201.09919/) (2022)
- [Language Model Analysis for Ontology Subsumption Inference](https://mlsanity.com/paper/2302.06761/) (2023)
- [Dual Box Embeddings for the Description Logic EL++](https://mlsanity.com/paper/2301.11118/) (2023)
- [Are Large Language Models a Good Replacement of Taxonomies?](https://mlsanity.com/paper/2406.11131/) (2024)
- [End-to-End Ontology Learning with Large Language Models](https://mlsanity.com/paper/2410.23584/) (2024)
- [Ontology Embedding: A Survey of Methods, Applications and Resources](https://mlsanity.com/paper/2406.10964/) (2024)
- [Signature-Based Abduction for Expressive Description Logics -- Technical Report](https://mlsanity.com/paper/2007.00757/) (2020)
- [Axiom Pinpointing](https://mlsanity.com/paper/2003.08298/) (2020)
- [OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learning](https://mlsanity.com/paper/2505.11031/) (2025)
- [Connection-minimal Abduction in EL via Translation to FOL -- Technical Report](https://mlsanity.com/paper/2205.08449/) (2022)
- [TransBox: EL++-closed Ontology Embedding](https://mlsanity.com/paper/2410.14571/) (2024)
- [Language Models as Ontology Encoders](https://mlsanity.com/paper/2507.14334/) (2025)
- [Large Language Model for OWL Proofs](https://mlsanity.com/paper/2601.12444/) (2026)
- [Why not? Developing ABox Abduction beyond Repairs](https://mlsanity.com/paper/2507.21955/) (2025)
- [From Subsumption to Satisfiability: LLM-Assisted Active Learning for OWL Ontologies](https://mlsanity.com/paper/2604.16672/) (2026)

## Abstract (arXiv)

OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world ontologies are often incomplete, which pose challenges for reasoning. In this work, we focus on a fundamental subsumption reasoning problem: given an incomplete ontology and a candidate (non-entailed) subsumption, determine whether the subsumption is semantically plausible and, if so, providing a logically sound explanation containing potential missing axioms. This task unifies subsumption verification with ontology abduction, and generalizes the latter by removing the need for a predefined candidate set of missing axioms. To address this subsumption reasoning problem, we propose NeurOWL, an end-to-end neuro-symbolic framework that jointly performs verification and abduction, leveraging both formally defined semantics and textual semantics through Large Language Models and ontology embeddings. We evaluate NeurOWL on real-world ontologies across multiple domains, demonstrating strong and robust performance across different domains.