Actively Ontology Learning from Large Language Models

Active learning is a framework where a learner attempts to learn some kind of knowledge by posing questions to a teacher. In computational learning theory, classically, the questions made by the learner are called membership queries and are answered with ‘yes’ or ‘no’ (or equivalently, with ‘true’ or ‘false’). Here we consider that the teacher is a language model and study the case in which the knowledge is expressed as an ontology. To evaluate the approach, we present results showing the performance of GPT and other language models when answering whether valid expressions on existing EL are “true” or “false”.