Towards the Generation of Musical Explanations with GPT-3
This addresses the problem of enabling dialogue in human-AI music partnerships for more engaging interactions, but it is incremental as it highlights limitations rather than achieving new capabilities.
The study investigated GPT-3's ability to generate textual explanations for musical decisions when prompted with music representations, finding that it lacks the intelligence to truly understand these decisions, with a major barrier being the lack of data on artists' creative processes.
Open AI's language model, GPT-3, has shown great potential for many NLP tasks, with applications in many different domains. In this work we carry out a first study on GPT-3's capability to communicate musical decisions through textual explanations when prompted with a textual representation of a piece of music. Enabling a dialogue in human-AI music partnerships is an important step towards more engaging and creative human-AI interactions. Our results show that GPT-3 lacks the necessary intelligence to really understand musical decisions. A major barrier to reach a better performance is the lack of data that includes explanations of the creative process carried out by artists for musical pieces. We believe such a resource would aid the understanding and collaboration with AI music systems.