Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale

TL;DR

The paper introduces LOM, a unified large ontology model that constructs, aligns, and reasons over enterprise data, significantly improving accuracy in ontology completion and graph reasoning tasks.

Contribution

It presents a novel end-to-end framework integrating ontology construction, semantic alignment, and logical reasoning into a single architecture for enterprise data.

Findings

LOM-4B achieves 88.8% accuracy in ontology completion.

LOM-4B achieves 94% accuracy in complex graph reasoning.

Outperforms state-of-the-art large language models.

Abstract

While enterprises amass vast quantities of data, much of it remains chaotic and effectively dormant, preventing decision-making based on comprehensive information. Existing neuro-symbolic approaches rely on disjoint pipelines and struggle with error propagation. We introduce the large ontology model (LOM), a unified framework that seamlessly integrates ontology construction, semantic alignment, and logical reasoning into a single end-to-end architecture. LOM employs a construct-align-reason (CAR) pipeline, leveraging its unified architecture across all three stages: it first autonomously constructs a domain-specific ontological universe from raw data, then aligns neural generation with this structural reality using a graph-aware encoder and reinforcement learning, and finally executes deterministic reasoning over the constructed topology, node attributes and relation types. We evaluate LOM on a comprehensive benchmark constructed from diverse real-world enterprise datasets. Experimental results demonstrate that LOM-4B achieves 88.8% accuracy in ontology completion and 94% in complex graph reasoning tasks, significantly outperforming state-of-the-art LLMs. These findings validate that autonomous logical construction is essential for achieving deterministic, enterprise-grade intelligence.