和声回路:符号音乐模型中和声进行源于稀疏主信息流
Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models
AI 导读
一项机制可解释性研究在 ChatMusician 与 MuPT 两个符号音乐生成模型中识别出与音乐功能相关的回路,研究对象是 I…V→I 经典和声进行中终止主音根音的预测。
正文 · 原文
Abstract:Mechanistic Interpretability (MI) seeks to decode neural network computations into human-understandable logic. A core methodology in MI is circuit discovery: identifying the information flow in sub-networks that drive specific model behaviors. While circuit discovery has matured within Natural Language Processing (NLP), the interpretable circuits in music models remain largely unexplored. In this work, we identify a music-functional circuit within two symbolic music generative models: ChatMusician and MuPT. The music function we consider is the prediction of the terminal tonic root in a classical harmonic progression pattern $I \ldots V \rightarrow I$. We use the Auto-Emergence algorithm to extract a principal sparse sub-network as the identified circuit. Validation via causal intervention confirms that this identified circuit is a primary driver of harmonic progression behaviors in the symbolic music models. To our knowledge, this represents the first systematic circuit-discovery study conducted within the music domain. Our demo page is available at: this https URL.
| Comments: | Accepted at the NeurIPS 2026 Workshop on Interpretability for Discovery. 12 pages, 6 figures |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.24453 [cs.SD] |
| (or arXiv:2611.24453v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24453 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ruiji Yu [view email]
[v1]
Wed, 18 Nov 2026 14:01:33 UTC (361 KB)
来源:arXiv cs.AI · arxiv.org