Towards Ontology Construction with Language Models
This addresses the problem of ontology construction for researchers or practitioners in knowledge representation, but it is incremental as it applies existing LLMs to a new application without major methodological innovation.
The authors tackled the problem of automatically constructing concept hierarchies for various domains by querying a large language model, specifically OpenAI's GPT-3.5, and found that LLMs can be of considerable help for this task.
We present a method for automatically constructing a concept hierarchy for a given domain by querying a large language model. We apply this method to various domains using OpenAI's GPT 3.5. Our experiments indicate that LLMs can be of considerable help for constructing concept hierarchies.