{"slug": "generative-ontology-induction-domain-agnostic-schema-discovery-from-document", "title": "Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models", "summary": "A new framework called Generative Ontology Induction (GOI) achieves 95-100% structural coverage across four diverse ontologies, according to a preprint on arXiv. The domain-agnostic method induces a typed graph with six node types and seven edge types from document corpora using large language models, outperforming a generic three-field template that dropped to 52.2% on a job description ontology.", "body_md": "arXiv:2607.16201v1 Announce Type: new\nAbstract: Ontology engineering remains a critical bottleneck in knowledge-intensive AI systems. Existing automated approaches either depend on predefined schemas, operate within narrow domains, or produce unstructured outputs unsuitable for downstream pipelines.\nWe introduce Generative Ontology Induction (GOI), a domain-agnostic framework that induces a generative blueprint - entities, dimensions, properties, relationships, and constraints - from a corpus of examples and exports it as a typed graph (six node types, seven edge types) in YAML/JSON. We introduce the Node Coverage Score, a novel evaluation metric that measures the fraction of structural ontology nodes (classes, properties, and dimensions) appearing in generated outputs.\nA controlled generative validation on four contrasting ontologies - a familiar Software Services Invoice schema, a custom Job Description Ontology, a confidential Pain-Management Clinical Visit Record Ontology, and a Professional Services Contract & Statement of Work Ontology - shows that GOI-prompted generation covers 95-100% of the structural backbone in every case; a generic three-field template holds at 97.8% on the invoice schema but drops to 52.2% on the Job Description Ontology, 62.2% on the Pain-Management ontology, and 78.3% on the Professional Services Contract ontology. The structural coverage holds regardless of how familiar the document type is to the model.", "url": "https://wpnews.pro/news/generative-ontology-induction-domain-agnostic-schema-discovery-from-document", "canonical_source": "https://arxiv.org/abs/2607.16201", "published_at": "2026-07-21 04:00:00+00:00", "updated_at": "2026-07-21 04:06:32.190608+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-tools"], "entities": ["Generative Ontology Induction", "arXiv", "Software Services Invoice", "Job Description Ontology", "Pain-Management Clinical Visit Record Ontology", "Professional Services Contract & Statement of Work Ontology"], "alternates": {"html": "https://wpnews.pro/news/generative-ontology-induction-domain-agnostic-schema-discovery-from-document", "markdown": "https://wpnews.pro/news/generative-ontology-induction-domain-agnostic-schema-discovery-from-document.md", "text": "https://wpnews.pro/news/generative-ontology-induction-domain-agnostic-schema-discovery-from-document.txt", "jsonld": "https://wpnews.pro/news/generative-ontology-induction-domain-agnostic-schema-discovery-from-document.jsonld"}}