mlsanityData to 14 Oct 2026

No Encore: Unlearning as Opt-Out in Music Generation

arXiv 2509.06277 ↗First posted 8 Sep 2025cs.CLcited by 1

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

AI music generation is rapidly emerging in the creative industries, enabling intuitive music generation from textual descriptions. However, these systems pose risks in exploitation of copyrighted creations, raising ethical and legal concerns. In this paper, we present preliminary results on the first application of machine unlearning techniques from an ongoing research to prevent inadvertent usage of creative content. Particularly, we explore existing methods in machine unlearning to a pre-trained Text-to-Music (TTM) baseline and analyze their efficacy in unlearning pre-trained datasets without harming model performance. Through our experiments, we provide insights into the challenges of applying unlearning in music generation, offering a foundational analysis for future works on the application of unlearning for music generative models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 19 of its 34 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

19 of 34 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech27 Jul
  2. 2024Machine Unlearning in Generative AI: A Survey30 Jul
  3. 2024Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models13 Mar
  4. 2024Dissecting Language Models: Machine Unlearning via Selective Pruning2 Mar
  5. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  6. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep

Other references · 13

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  3. 2023Erasing Concepts from Diffusion Modelscited by 539
  4. 2023Simple and Controllable Music Generationcited by 488
  5. 2021Efficient Training of Audio Transformers with Patchoutcited by 226
  6. 2018Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithmscited by 225
  7. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
  8. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 32
  9. 2024Generative Unlearning for Any Identitycited by 19
  10. 2024MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Modelscited by 19
  11. 2024Presto! Distilling Steps and Layers for Accelerating Music Generationcited by 16
  12. 2025Video-Guided Text-to-Music Generation Using Public Domain Movie Collectionscited by 6
1 more
  1. 2025Hookpad Aria: A Copilot for Songwriterscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarkscited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2025Large-Scale Training Data Attribution for Music Generative Models via Unlearning
  2. 2025Aligning Generative Music AI with Human Preferences: Methods and Challenges
  3. 2024Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
  4. 2025TuneGenie: Reasoning-based LLM agents for preferential music generation
  5. 2023JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
  6. 2024MusicRL: Aligning Music Generation to Human Preferences
  7. 2026Auditing Training Data in Generative Music Models via Black-Box Membership Inference
  8. 2024Improving Controllability and Editability for Pretrained Text-to-Music Generation Models ↗