Metraipolis › archive › dc_152d80085160

From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editing — arXiv:2609.34994

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34994
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:25.553Z
SHA-256 of the archived text
0ca7b5ca34807d09fc035bebe2dba6abc09af10d2ca817ea4d0a3328c9af4f80
Stable URL of this page
https://metraipolis.com/documento/dc_152d80085160

How to cite

From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editing — arXiv:2609.34994 — arXiv (en), https://arxiv.org/abs/2609.34994 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_152d80085160 (Metraipolis archive dc_152d80085160, sha256 0ca7b5ca34807d09fc035bebe2dba6abc09af10d2ca817ea4d0a3328c9af4f80)
BibTeX
@misc{dc152d80085160,
  title = {From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editing — arXiv:2609.34994},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34994},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_152d80085160; sha256 0ca7b5ca34807d09fc035bebe2dba6abc09af10d2ca817ea4d0a3328c9af4f80},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34994. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most music-generation systems are still framed and evaluated primarily as producers of complete outputs, whereas composition often proceeds through successive revisions to a shared musical artifact. This paper studies a different use of a general-purpose instruction-following large language model: not as a one-shot music generator, but as a reusable operator over an evolving symbolic score. We formulate incremental composition as a sequence of operation-aware state transitions over persistent ABC notation, with explicit requirements on what each operation may change and what it must preserve. The interaction includes two artifact-initialization variants and three editing operations -- chord addition, inpainting, and transposition. We instantiate the formulation by adapting Llama 3.1 8B Instruct with Low-Rank Adaptation (LoRA) on 496,038 operation-aware dialogue records derived from Irish traditional music. The comparison with the unadapted model is used to test the feasibility of learning this interaction contract, not to claim novelty for fine-tuning itself. Across 500 dialogues per model (1,750 attempted output states), checker admission rises from 29.37% to 99.37%, while compliance conditional on admission rises from 0.7205 to 0.9798. Strict eligibility for reference-relative musical-feature analysis increases from 14 to 1,548 outputs, and Longest Common Subsequence analysis does not show a systematic increase in high-overlap sequences relative to held-out baselines under the specified protocol. The results support the technical feasibility of persistent, operation-aware symbolic editing with a general-purpose instruction LLM. They do not establish superior musical quality or human-AI co-creativity, which remain questions for musician-centered evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.34994 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.745Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).