Not that Groove: Zero-Shot Symbolic Music Editing
This work addresses the problem of rigid AI music generation for producers by enabling flexible symbolic editing, though it is incremental as it focuses on a specific domain (drum grooves).
The paper tackled symbolic music editing for drum grooves using zero-shot prompting with LLMs, achieving effective editing without labeled data by designing a creative interface format and providing an evaluation dataset aligned with musicians' judgment.
Most work in AI music generation focused on audio, which has seen limited use in the music production industry due to its rigidity. To maximize flexibility while assuming only textual instructions from producers, we are among the first to tackle symbolic music editing. We circumvent the known challenge of lack of labeled data by proving that LLMs with zero-shot prompting can effectively edit drum grooves. The recipe of success is a creatively designed format that interfaces LLMs and music, while we facilitate evaluation by providing an evaluation dataset with annotated unit tests that highly aligns with musicians' judgment.