LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation

An ontology is a scheme for structuring relationships between concepts in a domain, promoting data interoperability and system integration. However, poorly designed ontologies can lead to errors and performance issues. While systems engineering has standardized evaluation guidelines (e.g., ISO/IEC),...

Full description

Saved in:
Bibliographic Details
Main Authors: Seungyeon Kim, Donghyun Kim, Seokju Hwang, Kyong-Ho Lee, Kyunghwa Lee
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10971367/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324341728116736
author Seungyeon Kim
Donghyun Kim
Seokju Hwang
Kyong-Ho Lee
Kyunghwa Lee
author_facet Seungyeon Kim
Donghyun Kim
Seokju Hwang
Kyong-Ho Lee
Kyunghwa Lee
author_sort Seungyeon Kim
collection DOAJ
description An ontology is a scheme for structuring relationships between concepts in a domain, promoting data interoperability and system integration. However, poorly designed ontologies can lead to errors and performance issues. While systems engineering has standardized evaluation guidelines (e.g., ISO/IEC), ontology engineering lacks such standards, leading to various independent evaluation methods. One frequent issue among novice developers is the misuse of ontology restrictions, particularly ‘allValuesFrom’ and ‘someValuesFrom’, which can significantly impact the correctness and reliability of ontologies. However, existing studies have not adequately addressed effective methods for detecting such errors. To address this gap, we propose a context-aware verification framework utilizing large language models to detect and correct misuse in ontology restrictions. Unlike conventional methods, our framework integrates contextual descriptions derived from ontological axioms, enabling more accurate verification. Additionally, we introduce a clustering-based description generation method that systematically organizes contextual information, further enhancing verification accuracy. Experimental evaluation conducted on diverse ontology datasets suggests that contextual integration improves verification performance. Moreover, the clustering-based description generation improves restriction misuse detection and correction compared to traditional approaches. By automating ontology restriction verification, this study contributes significantly to enhancing the reliability of ontology evaluation and provides a foundation for developing more scalable and standardized verification techniques.
format Article
id doaj-art-8b09fc0e104e4c33bc5bf672fb62abd5
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8b09fc0e104e4c33bc5bf672fb62abd52025-08-20T03:48:45ZengIEEEIEEE Access2169-35362025-01-0113736037361810.1109/ACCESS.2025.356256010971367LLM-Assisted Ontology Restriction Verification With Clustering-Based Description GenerationSeungyeon Kim0Donghyun Kim1https://orcid.org/0000-0001-7724-5514Seokju Hwang2https://orcid.org/0009-0009-7705-6145Kyong-Ho Lee3https://orcid.org/0000-0002-1581-917XKyunghwa Lee4https://orcid.org/0009-0002-8789-1848Department of Computer Science, Yonsei University, Seoul, Republic of KoreaDepartment of Computer Science, Yonsei University, Seoul, Republic of KoreaDepartment of Computer Science, Yonsei University, Seoul, Republic of KoreaDepartment of Computer Science, Yonsei University, Seoul, Republic of KoreaSsangyong Information and Communications Corporation, Seoul, Republic of KoreaAn ontology is a scheme for structuring relationships between concepts in a domain, promoting data interoperability and system integration. However, poorly designed ontologies can lead to errors and performance issues. While systems engineering has standardized evaluation guidelines (e.g., ISO/IEC), ontology engineering lacks such standards, leading to various independent evaluation methods. One frequent issue among novice developers is the misuse of ontology restrictions, particularly ‘allValuesFrom’ and ‘someValuesFrom’, which can significantly impact the correctness and reliability of ontologies. However, existing studies have not adequately addressed effective methods for detecting such errors. To address this gap, we propose a context-aware verification framework utilizing large language models to detect and correct misuse in ontology restrictions. Unlike conventional methods, our framework integrates contextual descriptions derived from ontological axioms, enabling more accurate verification. Additionally, we introduce a clustering-based description generation method that systematically organizes contextual information, further enhancing verification accuracy. Experimental evaluation conducted on diverse ontology datasets suggests that contextual integration improves verification performance. Moreover, the clustering-based description generation improves restriction misuse detection and correction compared to traditional approaches. By automating ontology restriction verification, this study contributes significantly to enhancing the reliability of ontology evaluation and provides a foundation for developing more scalable and standardized verification techniques.https://ieeexplore.ieee.org/document/10971367/Ontology evaluationontology restriction verificationtext generationclustering
spellingShingle Seungyeon Kim
Donghyun Kim
Seokju Hwang
Kyong-Ho Lee
Kyunghwa Lee
LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
IEEE Access
Ontology evaluation
ontology restriction verification
text generation
clustering
title LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
title_full LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
title_fullStr LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
title_full_unstemmed LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
title_short LLM-Assisted Ontology Restriction Verification With Clustering-Based Description Generation
title_sort llm assisted ontology restriction verification with clustering based description generation
topic Ontology evaluation
ontology restriction verification
text generation
clustering
url https://ieeexplore.ieee.org/document/10971367/
work_keys_str_mv AT seungyeonkim llmassistedontologyrestrictionverificationwithclusteringbaseddescriptiongeneration
AT donghyunkim llmassistedontologyrestrictionverificationwithclusteringbaseddescriptiongeneration
AT seokjuhwang llmassistedontologyrestrictionverificationwithclusteringbaseddescriptiongeneration
AT kyongholee llmassistedontologyrestrictionverificationwithclusteringbaseddescriptiongeneration
AT kyunghwalee llmassistedontologyrestrictionverificationwithclusteringbaseddescriptiongeneration