EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Alexbek at LLMs4OL 2025 Tasks A, B, and C: Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)

Aleksandra Beliaeva, Temurbek Rahmatullaev

Open Conference Proceedings · 01.10.2025 · 6

DOI: 10.52825/ocp.v6i.2899 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 01.10.2025. Verfasst von Aleksandra Beliaeva und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 7 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines retrieval-augmented prompting, zero-shot classification, and attention-based graph modeling — each tailored to the demands of the respective task. For Task A, we jointly extract domain-specific terms and their ontological types using a retrieval-augmented generation (RAG) pipeline.Training data was reformulated into a document to terms and types correspondence, while test-time inference leverages semantically similar training examples. This single-pass method requires no model finetuning and improves overall performance through lexical augmentation Task B, which involves assigning types to given terms, is handled via a dual strategy. In the few-shot setting (for domains with labeled training data), we reuse the RAG scheme with few-shot prompting. In the zero-shot setting (for previously unseen domains), we use a zero-shot classifier that combines cosine similarity scores from multiple embedding models using confidence-based weighting. In Task C, we model taxonomy discovery as graph inference. Using embeddings of type labels, we train a lightweight cross-attention layer to predict is-a relations by approximating a soft adjacency matrix. These modular, task-specific solutions enabled us to achieve top-ranking results in the official leaderboard across all three tasks. Taken together these strategies showcase the scalability, adaptability, and robustness of LLM-based architectures for ontology learning across heterogeneous domains. Code is available at: https://github.com/BelyaevaAlex/LLMs4OL-Challenge-Alexbek

Förderung

  • Russian Science Foundation

Zitieren

APA

Beliaeva, A., & Rahmatullaev, T. (2025). Alexbek at LLMs4OL 2025 Tasks A, B, and C: Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies). Open Conference Proceedings, 6. https://doi.org/10.52825/ocp.v6i.2899

Vancouver

Beliaeva A, Rahmatullaev T. Alexbek at LLMs4OL 2025 Tasks A, B, and C: Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies). Open Conference Proceedings. 2025;6. doi:10.52825/ocp.v6i.2899

BibTeX
@article{Beliaeva2025,
  author = {Beliaeva, Aleksandra and Rahmatullaev, Temurbek},
  title = {Alexbek at LLMs4OL 2025 Tasks A, B, and C: Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)},
  journal = {Open Conference Proceedings},
  year = {2025},
  volume = {6},
  doi = {10.52825/ocp.v6i.2899}
}
Kostenlos starten →