A modular, finetuning-free pipeline combining RAG prompting, zero-shot embedding ensembles, and attention-based graph inference achieves top leaderboard results on the LLMs4OL 2025 ontology learning tasks.
LLMs4OL: Large Language Models for Ontology Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose the LLMs4OL approach, which utilizes Large Language Models (LLMs) for Ontology Learning (OL). LLMs have shown significant advancements in natural language processing, demonstrating their ability to capture complex language patterns in different knowledge domains. Our LLMs4OL paradigm investigates the following hypothesis: \textit{Can LLMs effectively apply their language pattern capturing capability to OL, which involves automatically extracting and structuring knowledge from natural language text?} To test this hypothesis, we conduct a comprehensive evaluation using the zero-shot prompting method. We evaluate nine different LLM model families for three main OL tasks: term typing, taxonomy discovery, and extraction of non-taxonomic relations. Additionally, the evaluations encompass diverse genres of ontological knowledge, including lexicosemantic knowledge in WordNet, geographical knowledge in GeoNames, and medical knowledge in UMLS.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)
A modular, finetuning-free pipeline combining RAG prompting, zero-shot embedding ensembles, and attention-based graph inference achieves top leaderboard results on the LLMs4OL 2025 ontology learning tasks.