用方向向量精准控制音乐生成的节奏与音色，让模型可解释性更强。
Activation Patching for Interpretable Steering in Music Generation
- 通过差异均值法提取音乐属性的方向向量，实现连续调节。
- 在不损失音质前提下，成功调控快慢与明暗等二元音乐特征。
- 适用于需要精细控制音乐风格的研究者与创作者。
理解大型音频模型如何表示音乐，并利用这一理解来引导生成，既具挑战性又研究不足。受语言模型中变换器残差流方向向量用于分析与控制的启发，本文首次研究大型音频模型中的隐含方向向量及其在文本到音乐生成中对音乐属性的连续控制应用。聚焦于节奏（快/慢）和音色（明亮/阴暗）等二元概念，我们使用差异均值法在精心筛选的提示集上计算控制向量。这些向量经系数缩放后注入中间激活层，可在保持整体音频质量的前提下，实现对特定音乐特性的细粒度调节。我们分析了控制强度的影响，比较了不同注入策略，并识别出影响最大的网络层。研究结果表明，基于方向的控制是一种更具机制性和可解释性的可控音乐生成方法。
原文摘要 · Abstract (English)
Understanding how large audio models represent music, and using that understanding to steer generation, is both challenging and underexplored. Inspired by mechanistic interpretability in language models, where direction vectors in transformer residual streams are key to model analysis and control, we investigate similar techniques in the audio domain. This paper presents the first study of latent direction vectors in large audio models and their use for continuous control of musical attributes in text-to-music generation. Focusing on binary concepts like tempo (fast vs. slow) and timbre (bright vs. dark), we compute steering vectors using the difference-in-means method on curated prompt sets. These vectors, scaled by a coefficient and injected into intermediate activations, allow fine-grained modulation of specific musical traits while preserving overall audio quality. We analyze the effect of steering strength, compare injection strategies, and identify layers with the greatest influence. Our findings highlight the promise of direction-based steering as a more mechanistic and interpretable approach to controllable music generation.
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。