# Large-Scale Training Data Attribution for Music Generative Models via Unlearning

arXiv: https://arxiv.org/abs/2506.18312 · HTML: https://mlsanity.com/paper/2506.18312/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2025.

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

- [Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems](https://mlsanity.com/paper/2510.08062/) (2025)
- [Prototype Language Models](https://mlsanity.com/paper/2607.00510/) (2026)
- [Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew](https://mlsanity.com/paper/2605.17938/) (2026)
- [What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music](https://mlsanity.com/paper/2607.00641/) (2026)
- [GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning](https://mlsanity.com/paper/2601.22651/) (2026)
- [Data Attribution in Large Language Models via Bidirectional Gradient Optimization](https://mlsanity.com/paper/2606.04928/) (2026)
- [Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation](https://mlsanity.com/paper/2609.39552/) (2026)
- [TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models](https://mlsanity.com/paper/2610.00835/) (2026)
- [Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation](https://mlsanity.com/paper/2610.09637/) (2026)

## Abstract (arXiv)

This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the generation of a particular output from a specific model. This is crucial in the context of AI-generated music, where proper recognition and credit for original artists are generally overlooked. By enabling white-box attribution, our work supports a fairer system for acknowledging artistic contributions and addresses pressing concerns related to AI ethics and copyright. We apply unlearning-based attribution to a text-to-music diffusion model trained on a large-scale dataset and investigate its feasibility and behavior in this setting. To validate the method, we perform a grid search over different hyperparameter configurations and quantitatively evaluate the consistency of the unlearning approach. We then compare attribution patterns from unlearning with non-counterfactual approaches. Our findings suggest that unlearning-based approaches can be effectively adapted to music generative models, introducing large-scale TDA to this domain and paving the way for more ethical and accountable AI systems for music creation.