We explore the use of large language models (LLMs) for music generation using a retrieval system to select relevant examples. We find promising initial results for music generation in a dialogue with the user, especially considering the ease with which such a system can be implemented. The code is available online.
@article{arxiv.2311.10384,
title = {Retrieval Augmented Generation of Symbolic Music with LLMs},
author = {Nicolas Jonason and Luca Casini and Carl Thomé and Bob L. T. Sturm},
journal= {arXiv preprint arXiv:2311.10384},
year = {2023}
}