EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Genuineknowledge-KEOL at LLMs4OL 2026 Tasks Flagship, Reuse, and Taxonomy: Hybrid Training-Free Pipelines for Ontology and Taxonomy Discovery

Lvting Liu, Yubin Luo, Ji Qi, Chun Zheng, Chengli Zhong, Yi Zhou

Open Conference Proceedings · 02.11.2026 · 11

DOI: 10.52825/ocp.v11i.3661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 02.11.2026. Verfasst von Lvting Liu und 5 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ontology learning traditionally requires substantial domain expertise and curated corpora. This paper presents our systems for the three tracks of the LLMs4OL 2026 shared tasks: Task A: end-to-end ontology learning from raw text; Task B: extension of a partial ontology with new concepts and relations extracted from text; and Task C: cross-domain taxonomy learning. Our approach is entirely training-free: no model is fine-tuned, and no external knowledge bases are introduced. Rather than a single shared pipeline, the three systems follow a common design philosophy—stage-wise construction that pairs the semantic reasoning of instruction-tuned large language models, deterministic post-processing, and task-specific modules—but each task instantiates this philosophy differently. For Task A, we instantiate this framework as a domain-aware, multi-stage pipeline that retrieves in-domain demonstrations to progressively extracts and refines ontology elements. For Task B, we extend partial ontologies through domain-aware candidate verification, while using a three-model debate and ensemble mechanism to resolve conflicting concept and relation predictions. For Task C, which requires substantial domain knowledge and involves datasets of varying sizes, we employ models with stronger domain expertise together with size-adaptive chunking and rule-guided taxonomy extraction. Our work showcases how carefully orchestrated prompting, retrieval, and deterministic rules can deliver strong ontology learning results in a fully training-free setting.

Zitieren

APA

Liu, L., Luo, Y., Qi, J., Zheng, C., Zhong, C., & Zhou, Y. (2026). Genuineknowledge-KEOL at LLMs4OL 2026 Tasks Flagship, Reuse, and Taxonomy: Hybrid Training-Free Pipelines for Ontology and Taxonomy Discovery. Open Conference Proceedings, 11. https://doi.org/10.52825/ocp.v11i.3661

Vancouver

Liu L, Luo Y, Qi J, Zheng C, Zhong C, Zhou Y. Genuineknowledge-KEOL at LLMs4OL 2026 Tasks Flagship, Reuse, and Taxonomy: Hybrid Training-Free Pipelines for Ontology and Taxonomy Discovery. Open Conference Proceedings. 2026;11. doi:10.52825/ocp.v11i.3661

BibTeX
@article{Liu2026,
  author = {Liu, Lvting and Luo, Yubin and Qi, Ji and Zheng, Chun and Zhong, Chengli and Zhou, Yi},
  title = {Genuineknowledge-KEOL at LLMs4OL 2026 Tasks Flagship, Reuse, and Taxonomy: Hybrid Training-Free Pipelines for Ontology and Taxonomy Discovery},
  journal = {Open Conference Proceedings},
  year = {2026},
  volume = {11},
  doi = {10.52825/ocp.v11i.3661}
}
Kostenlos starten →