对比不同微调方法在乐谱生成与理解中的表现，揭示通用大模型适配音乐任务的权衡。
How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation
- 采用受控对比实验，比较指令微调与偏好优化等适配策略。
- 发现领域适配会损失原有知识，且不同评估指标行为差异显著。
- 适合研究音乐生成、大模型迁移的学者参考。
音乐与语言存在显著相似性，推动了预训练大语言模型（LLMs）在符号化音乐理解与生成中的应用。尽管关注度上升，但将指令微调的LLMs适配到符号化音乐任务的实际效果仍缺乏充分刻画。本文针对基于ABC表示的音乐生成与理解任务，开展受控对比研究，比较现成指令微调模型、领域适配变体及音乐专用模型基线。在多个符号化音乐数据集与评估指标上，揭示了领域适配与保留先验信息之间的权衡，以及用于衡量音乐领域适配的不同指标所表现出的差异行为。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。