This paper conducts a systematic empirical study of several state-of-the-art LLMs under different prompting strategies, isolating the role of structural guidance and contextual information in generating valid mappings and highlighting both the potential and the limitations of LLMs in structured semantic generation tasks.
The results suggest that OntoExtend is useful as a drafting assistant for requirement-driven ontology extension in real world scenarios, while remaining sensitive to CQ specificity and modelling profile.
Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid et al.· arXiv.org· 1 citation
The results support the feasibility of ontology-driven generation for static-classification systems, whereas arithmetic risk computation and temporal event processing remain better suited to complementary procedural technologies.
Borivoj Bogdanović, S. Nikolić· Computers· 0 citations
This study contributes a systematic workflow for metadata mapping and provides empirical evidence on the limitations of current metadata standardization practices, supporting future efforts toward improved cross-domain metadata interoperability.
Yan Cong, Masao Takaku, Yasuyuki Minamiyama et al.· 0 citations
The goal of this work is to put into context recent updates in ontology engineering and present the necessary additional information targeted to reuse by providing an updated overview and proposing a two-tier categorisation, believed to be the first review to offer such an intra-category classification.
Davide Di Pierro, L. Abrouk, A. Guyot et al.· 0 citations
LAMP (LLM-Assisted Mapping Pipeline), a novel approach that leverages Large Language Models (LLMs) to assist the mapping process in OBDI, is introduced, demonstrating significant improvements in F1-scores–particularly in complex mapping scenario–compared to single-prompt approach.
Sulthoni Ashiddiiqi, Fajar J. Ekaputra, M. Zuhri et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.