HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling
This addresses the challenge of format complexity and inconsistency in symbolic music generation for LLM applications, though it appears incremental as an extension of YNote.
The authors tackled the problem of symbolic music generation with LLMs by proposing HNote, a hexadecimal-based notation system that encodes pitch and duration in a fixed 32-unit measure framework, which achieved an 82.5% syntactic correctness rate and strong BLEU/ROUGE scores for stylistically coherent compositions.
Recent advances in large language models (LLMs) have created new opportunities for symbolic music generation. However, existing formats such as MIDI, ABC, and MusicXML are either overly complex or structurally inconsistent, limiting their suitability for token-based learning architectures. To address these challenges, we propose HNote, a novel hexadecimal-based notation system extended from YNote, which encodes both pitch and duration within a fixed 32-unit measure framework. This design ensures alignment, reduces ambiguity, and is directly compatible with LLM architectures. We converted 12,300 Jiangnan-style songs generated from traditional folk pieces from YNote into HNote, and fine-tuned LLaMA-3.1(8B) using parameter-efficient LoRA. Experimental results show that HNote achieves a syntactic correctness rate of 82.5%, and BLEU and ROUGE evaluations demonstrate strong symbolic and structural similarity, producing stylistically coherent compositions. This study establishes HNote as an effective framework for integrating LLMs with cultural music modeling.