Metraipolis › archive › dc_1028be4e6c58

pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning — arXiv:2608.27101

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27101
License (as archived)
CC0-1.0
Archived
2026-10-17T14:23:26.410Z
SHA-256 of the archived text
8c2a1ff7b794cb0a4d3593d26dcf96b5dd07fc6fd32fd1cf9eb093f64c2d3af3
Stable URL of this page
https://metraipolis.com/documento/dc_1028be4e6c58

How to cite

pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning — arXiv:2608.27101 — arXiv (en), https://arxiv.org/abs/2608.27101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1028be4e6c58 (Metraipolis archive dc_1028be4e6c58, sha256 8c2a1ff7b794cb0a4d3593d26dcf96b5dd07fc6fd32fd1cf9eb093f64c2d3af3)
BibTeX
@misc{dc1028be4e6c58,
  title = {pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning — arXiv:2608.27101},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27101},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1028be4e6c58; sha256 8c2a1ff7b794cb0a4d3593d26dcf96b5dd07fc6fd32fd1cf9eb093f64c2d3af3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produce inconsistent formats, and favor hierarchical over associative relations. In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Extension Reuse Task (Task B) using an offline retrieval-augmented few-shot prompting pipeline. Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B. A left-truncated context-windowing strategy preserves task instructions within long prompts. For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's closed term/type vocabulary and removing duplicates of the initial ontology. The approach achieves Semantic Graph Similarity of 0.8692, Term-Typing F1 of 0.9200, and Taxonomy Discovery F1 of 0.8540 on Task B, while Task A achieves 0.7416 Semantic Graph Similarity. However, no non-taxonomic relations are extracted, highlighting limitations of closed, taxonomy-oriented relation vocabularies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27101 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.544Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).