Exploring Large Language Models as a Source of Common-Sense Knowledge for Robots
This addresses the challenge of implicit common-sense knowledge for service robots, though it is incremental in combining LLMs with formal knowledge representation.
The paper tackled the problem of providing common-sense knowledge to service robots by exploring Large Language Models (LLMs) as a source, finding limited effectiveness for selective extraction but potential for large-scale extraction to efficiently create ontologies.
Service robots need common-sense knowledge to help humans in everyday situations as it enables them to understand the context of their actions. However, approaches that use ontologies face a challenge because common-sense knowledge is often implicit, i.e., it is obvious to humans but not explicitly stated. This paper investigates if Large Language Models (LLMs) can fill this gap. Our experiments reveal limited effectiveness in the selective extraction of contextual action knowledge, suggesting that LLMs may not be sufficient on their own. However, the large-scale extraction of general, actionable knowledge shows potential, indicating that LLMs can be a suitable tool for efficiently creating ontologies for robots. This paper shows that the technique used for knowledge extraction can be applied to populate a minimalist ontology, showcasing the potential of LLMs in synergy with formal knowledge representation.