Nov 2026· Open Conference Proceedings· Vol 11· 1 citation· 55 references
TL;DR
This work explores how LLM-assisted ontology-learning workflows can be adapted to different forms of textual and structured input, and develops task-specific methods that combine LLM prompting, NLP-based extraction, ontology context, cross-domain classification, and embedding-based downselection.
Abstract
Ontology learning aims to transform unstructured or semi-structured information into structured representations of domain knowledge. Large language models (LLMs) offer promising capabilities for automating parts of this process, but their effectiveness depends on the type of information available, including source text, partial ontologies, and related ontologies from other domains. This paper presents our submission to the LLMs4OL Challenge 2026, where we address three ontology-learning tasks: the Flagship Task, focused on ontology construction from text; the Reuse Task, focused on extending a partial ontology using text and existing triples; and the Taxonomy Task, focused on identifying taxonomic relations in a target domain using ontologies from other domains. Across these tasks, we develop task-specific methods that combine LLM prompting, NLP-based extraction, ontology context, cross-domain classification, and embedding-based downselection. Our work explores how LLM-assisted ontology-learning workflows can be adapted to different forms of textual and structured input.
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 ontol...
Hamed Babaei Giglou, Sören Auer, Jennifer D'Souza· Open Conference Proceedings· 7 citations· ⚡2
This volume collects the contributions to the 3rd LLMs4OL Challenge, Large Language Models for Ontology Learning, held at the 25th International Semantic Web Conference (ISWC 2026).
The LLMs4OL initiative began with a narrow question: can large language models perform the individual operations that ontology learning ta...
Hamed Babaei Giglou, Sören Auer, Jennifer D'Souza· Open Conference Proceedings· 3 citations
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 tex...
Lvting Liu, Yu-Bin Luo, Ji Qi et al.· Open Conference Proceedings· 1 citation
Large language models can generate ontology elements, but the evidence and output constraints differ across document extraction, graph extension, and taxonomy induction. This paper presents the Volt-IQ systems for LLMs4OL 2026 Tasks Flagship, Reuse, and Taxonomy. A shared processing contract routes each task to a diffe...
Erban Ku, Ding Nie· Open Conference Proceedings· 0 citations
The LLMs4OL 2026 Flagship and Reuse tasks expose two complementary ontology-learning settings: constructing a primitive ontology from raw text and extending a supplied partial ontology. We study both through one design question: how should the available task structure bound a language model’s semantic decisions? Our an...
Chu-Han Deng, Yu-Qi Fan, Can Zeng et al.· Open Conference Proceedings· 1 citation
This paper presents team LaboroAI's participation in the LLMs4OL 2026 Challenge, covering the Flagship task (end-to-end ontology learning from text) and the Reuse task (extending a given seed ontology). Both systems share one deliberately simple design: a single LLM call per document, grounded by few-shot exemplars ret...
Xin-Yi Zhao, Jia-Cheng Xu· Open Conference Proceedings· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.