Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918467595141120 |
|---|---|
| author | Talukder, Abid Mridul, Maruf Ahmed Seneviratne, Oshani |
| author_facet | Talukder, Abid Mridul, Maruf Ahmed Seneviratne, Oshani |
| contents | Automatically generating formal ontologies from unstructured natural language remains a central challenge in knowledge engineering. While large language models (LLMs) show promise, it remains unclear which architectural design choices drive generation quality and why current approaches fail. We present a controlled experimental study using domain-specific insurance contracts to investigate these questions. We first establish a single-agent LLM baseline, identifying key failure modes such as poor Ontology Design Pattern compliance, structural redundancy, and ineffective iterative repair. We then introduce a multi-agent architecture that decomposes ontology construction into four artifact-driven roles: Domain Expert, Manager, Coder, and Quality Assurer. We evaluate performance across architectural quality (via a panel of heterogeneous LLM judges) and functional usability (via competency question driven SPARQL evaluation with complementary retrieval augmented generation based assessment). Results show that the multi-agent approach significantly improves structural quality and modestly enhances queryability, with gains driven primarily by front-loaded planning. These findings highlight planning-first, artifact-driven generation as a promising and more auditable path toward scalable automated ontology engineering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23090 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach Talukder, Abid Mridul, Maruf Ahmed Seneviratne, Oshani Artificial Intelligence Automatically generating formal ontologies from unstructured natural language remains a central challenge in knowledge engineering. While large language models (LLMs) show promise, it remains unclear which architectural design choices drive generation quality and why current approaches fail. We present a controlled experimental study using domain-specific insurance contracts to investigate these questions. We first establish a single-agent LLM baseline, identifying key failure modes such as poor Ontology Design Pattern compliance, structural redundancy, and ineffective iterative repair. We then introduce a multi-agent architecture that decomposes ontology construction into four artifact-driven roles: Domain Expert, Manager, Coder, and Quality Assurer. We evaluate performance across architectural quality (via a panel of heterogeneous LLM judges) and functional usability (via competency question driven SPARQL evaluation with complementary retrieval augmented generation based assessment). Results show that the multi-agent approach significantly improves structural quality and modestly enhances queryability, with gains driven primarily by front-loaded planning. These findings highlight planning-first, artifact-driven generation as a promising and more auditable path toward scalable automated ontology engineering. |
| title | Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.23090 |