@inproceedings{kumar-etal-2026-far,
    title = "How Far Can Pretrained {LLM}s Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation",
    author = "Kumar, Deepak  and
      Karystinaios, Emmanouil  and
      Widmer, Gerhard  and
      Schedl, Markus",
    editor = "Epure, Elena V.  and
      Oramas, Sergio  and
      Doh, SeungHeon  and
      Ramoneda, Pedro  and
      Kruspe, Anna  and
      Sordo, Mohamed",
    booktitle = "Proceedings of the 4th Workshop on {NLP} for Music and Audio ({NLP}4{M}us{A} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.nlp4musa-1.5/",
    pages = "27--32",
    ISBN = "979-8-89176-369-2",
    abstract = "Music often shares notable parallels with language, motivating the use of pretrained large language models (LLMs) for symbolic music understanding and generation. Despite growing interest, the practical effectiveness of adapting instruction-tuned LLMs to symbolic music remains insufficiently characterized. We present a controlled comparative study of finetuning strategies for ABC-based generation and understanding, comparing an off-the-shelf instruction-tuned backbone to domain-adapted variants and a music-specialized LLM baseline. Across multiple symbolic music corpora and evaluation signals, we provide some insights into adaptation choices for symbolic music applications. We highlight the domain adaptation vs.{~}preserving prior information tradeoff as well as the distinct behaviour of metrics used to measure the domain adaptation for symbolic music."
}