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

arXiv: https://arxiv.org/abs/2602.00029 · HTML: https://mlsanity.com/paper/2602.00029/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability](https://mlsanity.com/paper/2403.04483/) (2024)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [SDM-RDFizer: An RML Interpreter for the Efficient Creation of RDF Knowledge Graphs](https://mlsanity.com/paper/2008.07176/) (2020)
- [Large Language Models Can Better Understand Knowledge Graphs Than We Thought](https://mlsanity.com/paper/2402.11541/) (2024)
- [G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge](https://mlsanity.com/paper/2509.24276/) (2025)
- [GraphAgent: Agentic Graph Language Assistant](https://mlsanity.com/paper/2412.17029/) (2024)
- [Retrieval-Augmented Generation of Ontologies from Relational Databases](https://mlsanity.com/paper/2506.01232/) (2025)

## Built on by (most cited first, 2 of 2)

- [Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale](https://mlsanity.com/paper/2604.09608/) (2026)
- [From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI](https://mlsanity.com/paper/2604.08603/) (2026)

## Abstract (arXiv)

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.