2026· LLMS4KGOE/ELMKE@ESWC· pp. 163-176· 0 citations· 30 references
Computer Science
TL;DR
It is highlighted that effective ontology reuse with LLMs requires dedicated prompting, alignment mechanisms, LLM-ready ontology reuse methodologies and hybrid human-in-the-loop workflows to ensure ontology reuse operations are considered and implemented.
Ontologies support shared meaning across Semantic Web applications, but selecting an appropriate ontology for reuse remains difficult because existing candidates often differ in documentation quality, semantic clarity, structural connectivity, and logical soundness. Reuse decisions are therefore frequently based on fam...
A. Dalal, Mariam Baloch, A. Lin et al.· International Journal of Sem...· 0 citations
The results demonstrate the feasibility of the proposed framework for producing consistent sentence-level semantic extraction from quality-related construction requirement text and demonstrate how ontology-guided fine-tuning can provide explicit semantic grounding for LLM-based information extraction.
Lian-Nian Wang, Jeongbin Hwang, Kevin Han et al.· Journal of Management in Eng...· 0 citations
Ontology generation from Competency Questions (CQs) is a central yet labor-intensive phase of Ontology Engineering. While large language models (LLMs) offer promising automation capabilities, current evaluations remain fragmented. Task formulations are heterogeneous, gold standards often lack fine-grained CQ provenance...
Jia-Yi Li, Zi-Yuan Wang, D. Garijo et al.· arXiv.org· 1 citation
This paper examines related work on ontology-based middleware that supports semantic interoperability in multi-cloud environments and identifies future middleware design directions. It answers three research questions: how the field has developed, how ontology-based middleware can support shared meaning across heteroge...
Jin Zhang, N. Admodisastro, Norazian M. Hamdan et al.· International Journal on Adv...· 0 citations
Ontologies support reasoning, information retrieval, data
integration, and FAIR data practices by representing domain
knowledge as structured entities and relationships. They
are a fundamental component of neuro-symbolic AI systems,
providing risk mitigation for AI systems through
explicitly-encoded knowledge. Large la...
Ryn Gray, Jarod Kaltenbaugh, J. Murdock et al.· Proceedings of the AAAI Symp...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.