LLMs4OL: Large Language Models for Ontology Learning

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: $\mathit{\text{Can}}\mathit{\text{LLMs}}\mathit{\text{effectively}}\mathit{\text{apply}}\mathit{\text{their}}\mathit{\text{language}}\mathit{\text{pattern}}\mathit{\text{capturing}}\mathit{\text{capability}}\mathit{\text{to}}\mathit{\text{OL,}}\mathit{\text{which}}\mathit{\text{involves}}\mathit{\text{automatically}}\mathit{\text{extracting}}\mathit{\text{and}}\mathit{\text{structuring}}\mathit{\text{knowledge}}\mathit{\text{from}}\mathit{\text{natural}}\mathit{\text{language}}\mathit{\text{text?}}$ 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.