Skip to main navigation Skip to search Skip to main content

OntoInsight - A Metric-Guided Tool for Ontology Quality Evaluation with LLM-Powered Recommendations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Ontologies are foundational to conceptual modeling and semantic systems across diverse domains, yet evaluating and improving their quality remains a complex challenge. Existing tools often focus on syntactic correctness or complex metric reporting, lacking actionable and interpretable feedback, which is not very intuitive. We present an ontology quality evaluation tool, named OntoInsight, that caters to different types of users, from beginners to advanced, with custom recommendations, basic (simple suggestions), and advanced (involving deep technical insights) recommendations. It can handle ontologies of varying size with full ontology evaluation and modular evaluation (useful for large and complex ontologies). The pipeline automates all the stages in the tool, from metric computation (via frameworks such as OQuaRE) and seed-term-based modularization to controlled natural language (CNL) translation and targeted prompt generation for Large Language Models (LLMs). The user has the freedom to configure their own LLM API key and choose the type of evaluation and suggestions they want, according to their needs and expertise. The source code of OntoInsight is available under Apache 2.0 license at https://github.com/kracr/onto-insight.
Original languageEnglish
Title of host publicationConceptual Modeling, ER 2025
EditorsDominik Bork, Roman Lukyanenko, Shazia Sadiq, Ladjel Bellatreche, Oscar Pastor
PublisherSpringer Science and Business Media Deutschland GmbH
Pages393-411
Number of pages19
ISBN (Electronic)978-3-032-08623-5
ISBN (Print)978-3-032-08622-8
DOIs
StatePublished - 2025
Event44th International Conference on Conceptual Modeling, ER 2025 - Poitiers, France
Duration: Oct 20 2025Oct 23 2025

Publication series

NameLecture Notes in Computer Science
Volume16189 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference44th International Conference on Conceptual Modeling, ER 2025
Country/TerritoryFrance
CityPoitiers
Period10/20/2510/23/25

ASJC Scopus Subject Areas

  • Theoretical Computer Science
  • General Computer Science

Keywords

  • AI-Assisted Modeling
  • Computational Tool
  • Controlled Natural Language
  • Empirical Evaluation
  • Large Language Models
  • Modularization
  • Ontology Quality
  • Quality Paradigms and Metrics

Cite this