跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24453 · v1

Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models

首次提交 2026-11-18 22:01
版本更新 2026-11-18 22:01
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

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…V→II \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: https://ukiyo23rui.github.io/auto-emergence-demo/.

作者备注:Accepted at the NeurIPS 2026 Workshop on Interpretability for Discovery. 12 pages, 6 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 22:01 · 最新观测版本

Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models

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…V→II \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: https://ukiyo23rui.github.io/auto-emergence-demo/.

查看此版本解读 →查看此版本原文 ↗