Construct, Align, and Reason: Large Ontology Models for Enterprise Knowledge Management

TL;DR

This paper introduces a large ontology model (LOM) framework for enterprise knowledge management, combining structured and unstructured data with a multi-stage training pipeline to improve semantic reasoning and complex question answering.

Contribution

The paper proposes a novel construct--align--reason framework and a comprehensive training pipeline for large ontology models, enhancing enterprise knowledge integration and reasoning capabilities.

Findings

LOM achieves 89.47% accuracy on ontology reasoning tasks

LOM outperforms DeepSeek-V3.2 on complex graph reasoning

Effective fusion of ontology structure and language demonstrated

Abstract

Enterprise-scale knowledge management faces significant challenges in integrating multi-source heterogeneous data and enabling effective semantic reasoning. Traditional knowledge graphs often struggle with implicit relationship discovery and lack sufficient semantic understanding for complex question answering. To address these limitations, we introduce a unified construct--align--reason framework, the large ontology model (LOM). We first build a dual-layer enterprise ontology from structured databases and unstructured text, subsequently fusing these sources into a comprehensive enterprise ontology. To enable instruction-aligned reasoning, we propose a unified three-stage training pipeline: ontology instruction fine-tuning to improve structural understanding; text-ontology grounding to strengthen node semantic encoding; and multi-task instruction tuning on ontology-language pairs with curriculum learning to enhance semantic reasoning and generation. We also construct comprehensive training and evaluation datasets covering diverse ontology reasoning tasks. On this benchmark, our 4B-parameter LOM achieves 89.47% accuracy and outperforms DeepSeek-V3.2 on complex graph reasoning, indicating effective fusion of ontology structure and language.