EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLMs4OL 2026 Overview: The 3rd Large Language Models for Ontology Learning Challenge

Hamed Babaei Giglou, Sören Auer, Jennifer D’Souza

Open Conference Proceedings · 02.11.2026 · 11

DOI: 10.52825/ocp.v11i.3728 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 02.11.2026. Verfasst von Hamed Babaei Giglou und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present the results of the 3rd Large Language Models for Ontology Learning Challenge, held at the International Semantic Web Conference 2026, a shared task designed to evaluate the effectiveness of large language models (LLMs) for ontology learning. The challenge comprised three complementary tasks: end-to-end ontology construction from text (Flagship), extension of an existing partial ontology (Reuse), and cross-domain taxonomy discovery (Taxonomy). Participants explored a broad range of approaches, including general-purpose and adapted LLMs, embedding-based retrieval, conventional NLP pipelines, and hybrid symbolic methods. Results show that constraining the label space through a supplied vocabulary matters more than model scale, and that retrieval grounding and task-specific adaptation of open-weight models transferred more reliably than post-hoc correction. Persistent challenges include candidate retrieval, entity normalization, and complete taxonomy recovery, while non-taxonomic relation extraction was rarely attempted under the current scoring. Building on this edition, we are integrating submitted systems into OntoLearner, our modular framework for ontology learning, so challenge contributions remain reusable and comparable.

Förderung

  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Giglou, H. B., Auer, S., & D’Souza, J. (2026). LLMs4OL 2026 Overview: The 3rd Large Language Models for Ontology Learning Challenge. Open Conference Proceedings, 11. https://doi.org/10.52825/ocp.v11i.3728

Vancouver

Giglou HB, Auer S, D’Souza J. LLMs4OL 2026 Overview: The 3rd Large Language Models for Ontology Learning Challenge. Open Conference Proceedings. 2026;11. doi:10.52825/ocp.v11i.3728

BibTeX
@article{Giglou2026,
  author = {Giglou, Hamed Babaei and Auer, Sören and D’Souza, Jennifer},
  title = {LLMs4OL 2026 Overview: The 3rd Large Language Models for Ontology Learning Challenge},
  journal = {Open Conference Proceedings},
  year = {2026},
  volume = {11},
  doi = {10.52825/ocp.v11i.3728}
}
Kostenlos starten →