# SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders

arXiv: https://arxiv.org/abs/2503.14530 · HTML: https://mlsanity.com/paper/2503.14530/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 43 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)
- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (2023)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Steering Language Model Refusal with Sparse Autoencoders](https://mlsanity.com/paper/2411.11296/) (2024)
- [Improving Steering Vectors by Targeting Sparse Autoencoder Features](https://mlsanity.com/paper/2411.02193/) (2024)
- [Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference](https://mlsanity.com/paper/2406.08607/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders](https://mlsanity.com/paper/2501.18052/) (2025)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [Applying sparse autoencoders to unlearn knowledge in language models](https://mlsanity.com/paper/2410.19278/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [Private Attribute Inference from Images with Vision-Language Models](https://mlsanity.com/paper/2404.10618/) (2024)
- [A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models](https://mlsanity.com/paper/2503.01854/) (2025)

## Built on by (most cited first, 13 of 13)

- [VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set](https://mlsanity.com/paper/2510.21323/) (2025)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning](https://mlsanity.com/paper/2605.05909/) (2026)
- [Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models](https://mlsanity.com/paper/2605.08031/) (2026)
- [Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2605.10198/) (2026)
- [On the Robustness of Machine Unlearning for Vision-Language Models](https://mlsanity.com/paper/2605.26992/) (2026)
- [AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2608.28312/) (2026)
- [Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning](https://mlsanity.com/paper/2607.18615/) (2026)
- [What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models](https://mlsanity.com/paper/2608.24142/) (2026)
- [Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models](https://mlsanity.com/paper/2608.29996/) (2026)
- [Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models](https://mlsanity.com/paper/2609.17790/) (2026)
- [Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning](https://mlsanity.com/paper/2610.10358/) (2026)
- [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026)

## Abstract (arXiv)

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a coarse granularity, often leading to excessive forgetting and reduced model utility. To address this issue, we introduce SAUCE, a novel method that leverages sparse autoencoders (SAEs) for fine-grained and selective concept unlearning in VLMs. Briefly, SAUCE first trains SAEs to capture high-dimensional, semantically rich sparse features. It then identifies the features most relevant to the target concept for unlearning. During inference, it selectively modifies these features to suppress specific concepts while preserving unrelated information. We evaluate SAUCE on two distinct VLMs, LLaVA-v1.5-7B and LLaMA-3.2-11B-Vision-Instruct, across two types of tasks: concrete concept unlearning (objects and sports scenes) and abstract concept unlearning (emotions, colors, and materials), encompassing a total of 60 concepts. Extensive experiments demonstrate that SAUCE outperforms state-of-the-art methods by 18.04% in unlearning quality while maintaining comparable model utility. Furthermore, we investigate SAUCE's robustness against widely used adversarial attacks, its transferability across models, and its scalability in handling multiple simultaneous unlearning requests. Our findings establish SAUCE as an effective and scalable solution for selective concept unlearning in VLMs.