MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Challenge:	Recent advances in machine learning (MU) have enabled the selective removal of private or sensitive information encoded within deep neural networks.
Approach:	They propose to "reformulate" the task of multimodal MU in the era of MLLMs by preserving only the visual patterns associated with a given entity while preserving the corresponding textual knowledge.
Outcome:	The proposed method surpasses baselines that finetuned MLLMs with VQA data directly through Gradient Ascent (GA) or Negative Preference Optimization (NPO), across all evaluation dimensions.

Similar Papers

Overview

Challenge

Approach

Outcome

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models (2025.acl-long)

Copied to clipboard

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang, Zhaoxuan Tan, Meng Jiang

Semantic Text Processing

Challenge:	Large Language Models and Multimodal Large Language Modells can memorize sensitive information, raising ethical and privacy concerns.
Approach:	They propose a novel unlearning framework that selectively clips neurons based on their relative importance to the targeted forget data.
Outcome:	The proposed framework selectively clips neurons based on their relative importance to the targeted forget data, curated for different modalities.

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Hao Zheng, Zirui Pang, Ling Li, Zhijie Deng, Yuhan Pu, Zhaowei Zhu, Xiaobo Xia, Jiaheng Wei

Responsible & Trustworthy NLP

Challenge:	Existing benchmarks for MU are limited by a lack of image diversity and coarse-grained unlearning targets.
Approach:	They propose a benchmark to evaluate misinformation unlearning in MLLMs . OFFSIDE supports advanced unlearning targets such as fine-grained unlearning and visual rumor removal.
Outcome:	OFFSIDE supports advanced unlearning targets, such as fine-grained unlearning and visual rumor removal.

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)

Copied to clipboard

Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu

Language Models

Challenge:	Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs.
Approach:	They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility .
Outcome:	The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility.

SUA: Stealthy Multimodal Large Language Model Unlearning Attack (2025.emnlp-main)

Copied to clipboard

Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, Suhang Wang

Semantic Text Processing

Challenge:	Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing privacy and copyright concerns.
Approach:	They propose a framework that learns a universal noise pattern to recover unlearned information from MLLMs.
Outcome:	The proposed framework learns a universal noise pattern and can reveal unlearned content when applied to images.

CLEAR: Character Unlearning in Textual and Visual Modalities (2025.findings-acl)

Copied to clipboard

Alexey Dontsov, Dmitrii Korzh, Alexey Zhavoronkin, Boris Mikheev, Denis Bobkov, Aibek Alanov, Oleg Rogov, Ivan Oseledets, Elena Tutubalina

Multimodality

Challenge:	Existing methods for removing private or hazardous data from deep learning models are focused on single-modality models.
Approach:	They propose CLEAR, the first open-source benchmark specifically for MMU. CLEAR contains 200 fictitious individuals and 3,700 images linked with corresponding question-answer pairs.
Outcome:	The proposed benchmarks show that unlearning both modalities outperform single-modality approaches.

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks (2026.findings-acl)

Copied to clipboard

Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil

Multimodality

Challenge:	Survey aims to identify challenges of multimodal unlearning for vision, language, audio and video . retraining after deletion requests or policy updates is often impractical, survey finds .
Approach:	They propose to enable selective removal across modalities while retaining overall utility.
Outcome:	This study compares models with existing models to identify weaknesses and improves performance.

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Copied to clipboard

Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze

Multimodality

Challenge:	Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach:	They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome:	The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.

Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)

Copied to clipboard

Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi

Semantic Text Processing

Challenge:	Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs).
Approach:	They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD).
Outcome:	The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation.

LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport (2026.acl-long)

Copied to clipboard

Zekun Wang, Jingjie Zeng, Yingxu Li, Hongfei Lin, Liang Yang

Multimodality

Challenge:	Existing unlearning methods suffer from a geometric mismatch, causing catastrophic forgetting or unsafe substitution.
Approach:	They propose a framework for surgical semantic pruning within the Lorentz manifold.
Outcome:	Experiments on MLLMU-Bench show that LOTUS significantly outperforms baselines while maintaining general utility.

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench (2025.naacl-long)

Copied to clipboard

Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, Meng Jiang

Language Models

Challenge:	Large Language Models (LLMs) and Multimodal Large Language models (MLLMs) trained on vast web corpora can memorize and disclose individuals’ confidential and private data, raising legal and ethical concerns.
Approach:	They propose a benchmark to assess unlearning algorithms from multiple perspectives and provide a baseline for existing generative models.
Outcome:	The proposed benchmark consists of 500 fictitious profiles and 153 profiles for public celebrities, evaluated from both multimodal (image+text) and unimodal (text) perspectives.