# SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers

arXiv: https://arxiv.org/abs/2404.02252 · HTML: https://mlsanity.com/paper/2404.02252/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2024.

## Built on by (most cited first, 9 of 9)

- [Taming Data and Transformers for Audio Generation](https://mlsanity.com/paper/2406.19388/) (2024)
- [Steering Autoregressive Music Generation with Recursive Feature Machines](https://mlsanity.com/paper/2510.19127/) (2025)
- [TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument](https://mlsanity.com/paper/2502.08939/) (2025)
- [TADA! Tuning Audio Diffusion Models through Activation Steering](https://mlsanity.com/paper/2602.11910/) (2026)
- [Genre Controlled Music Generation via Activation Steering](https://mlsanity.com/paper/2506.10225/) (2025)
- [Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation](https://mlsanity.com/paper/2605.31295/) (2026)
- [Aligning Generative Music AI with Human Preferences: Methods and Challenges](https://mlsanity.com/paper/2511.15038/) (2025)
- [Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation](https://mlsanity.com/paper/2609.39552/) (2026)
- [Harmonic Representations in Symbolic Music Transformers are Localized and Controllable](https://mlsanity.com/paper/2610.15957/) (2026)

## Abstract (arXiv)

We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for controlling an autoregressive generative music transformer using classifier probes. These simple logistic regression probes are trained on the output of each attention head in the transformer using a small dataset of audio examples both exhibiting and missing a specific musical trait (e.g., the presence/absence of drums, or real/synthetic music). We then steer the attention heads in the probe direction, ensuring the generative model output captures the desired musical trait. Additionally, we monitor the probe output to avoid adding an excessive amount of intervention into the autoregressive generation, which could lead to temporally incoherent music. We validate our results objectively and subjectively for both audio continuation and text-to-music applications, demonstrating the ability to add controls to large generative models for which retraining or even fine-tuning is impractical for most musicians. Audio samples of the proposed intervention approach are available on our demo page http://tinyurl.com/smitin .