# SEMU: Singular Value Decomposition for Efficient Machine Unlearning

arXiv: https://arxiv.org/abs/2502.07587 · HTML: https://mlsanity.com/paper/2502.07587/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- First posted on arXiv 11 Feb 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Built on by (most cited first, 14 of 14)

- [Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models](https://mlsanity.com/paper/2601.06162/) (2026)
- [UnGuide: Learning to Forget with LoRA-Guided Diffusion Models](https://mlsanity.com/paper/2508.05755/) (2025)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [Geometric-disentangelment Unlearning](https://mlsanity.com/paper/2511.17100/) (2025)
- [Stitch: Training-Free Position Control in Multimodal Diffusion Transformers](https://mlsanity.com/paper/2509.26644/) (2025)
- [UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning](https://mlsanity.com/paper/2602.03410/) (2026)
- [LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection](https://mlsanity.com/paper/2508.06467/) (2025)
- [Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models](https://mlsanity.com/paper/2510.03263/) (2025)
- [Machine Unlearning in Low-Dimensional Feature Subspace](https://mlsanity.com/paper/2601.22456/) (2026)
- [BARRIER: Bounded Activation Regions for Robust Information Erasure](https://mlsanity.com/paper/2605.15737/) (2026)
- [Spectral Saliency for Machine Unlearning](https://mlsanity.com/paper/2608.15548/) (2026)
- [Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage](https://mlsanity.com/paper/2609.02091/) (2026)
- [Open Vocabulary Domain Unlearning](https://mlsanity.com/paper/2609.31356/) (2026)
- [State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting](https://mlsanity.com/paper/2610.02248/) (2026)

## Abstract (arXiv)

While the capabilities of generative foundational models have advanced rapidly in recent years, methods to prevent harmful and unsafe behaviors remain underdeveloped. Among the pressing challenges in AI safety, machine unlearning (MU) has become increasingly critical to meet upcoming safety regulations. Most existing MU approaches focus on altering the most significant parameters of the model. However, these methods often require fine-tuning substantial portions of the model, resulting in high computational costs and training instabilities, which are typically mitigated by access to the original training dataset. In this work, we address these limitations by leveraging Singular Value Decomposition (SVD) to create a compact, low-dimensional projection that enables the selective forgetting of specific data points. We propose Singular Value Decomposition for Efficient Machine Unlearning (SEMU), a novel approach designed to optimize MU in two key aspects. First, SEMU minimizes the number of model parameters that need to be modified, effectively removing unwanted knowledge while making only minimal changes to the model's weights. Second, SEMU eliminates the dependency on the original training dataset, preserving the model's previously acquired knowledge without additional data requirements. Extensive experiments demonstrate that SEMU achieves competitive performance while significantly improving efficiency in terms of both data usage and the number of modified parameters.