# YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation

arXiv: https://arxiv.org/abs/2502.10467 · HTML: https://mlsanity.com/paper/2502.10467/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Builds on (most cited first, 4 of 4)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Noise2Music: Text-conditioned Music Generation with Diffusion Models](https://mlsanity.com/paper/2302.03917/) (2023)
- [Tracking Naturalistic Linguistic Predictions with Deep Neural Language Models](https://mlsanity.com/paper/1909.04400/) (2019)
- [Understanding MIDI: A Painless Tutorial on Midi Format](https://mlsanity.com/paper/1705.05322/) (2017)

## Built on by (most cited first, 2 of 2)

- [Decoding Musical Origins: Distinguishing Human and AI Composers](https://mlsanity.com/paper/2509.11369/) (2025)
- [HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling](https://mlsanity.com/paper/2509.25694/) (2025)

## Abstract (arXiv)

The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote's fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs.