ACL Findings2025
MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xuming Hu
Abstract
Recent progress in Machine Unlearning (MU) has introduced solutions for the selective removal of private or sensitive information encoded within deep neural networks. Nonetheless, MU for Multimodal Large Language Models (MLLMs) remains in its nascent phase. Therefore, we propose to reformulate the task of multimodal MU in the era of MLLMs, which aims to erase only the visual patterns associated with a given entity while preserving the corresponding textual knowledge encoded within the original parameters of the language model backbone. Furthermore, we develop a novel geometry-constrained gradient ascent method MMUNLEARNER. It updates the weights of MLLMs with a weight saliency map jointly restricted by the remaining concepts and textual knowledge during unlearning, thereby preserving parameters essential for non-target knowledge. Extensive experiments demonstrate that MMUNLEARNER surpasses baselines that finetuning MLLMs with VQA data directly through Gradient Ascent (GA) or Negative Preference Optimization (NPO), across all evaluation dimensions. Our code can be found in this URL
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
8 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- SineProject: Machine Unlearning for Stable Vision-Language Alignment cites Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
- SineProject: Machine Unlearning for Stable Vision-Language Alignment cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- SineProject: Machine Unlearning for Stable Vision-Language Alignment cites Learning Transferable Visual Models From Natural Language Supervision
- VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models cites Learning Transferable Visual Models From Natural Language Supervision
- Align before Fuse: Vision and Language Representation Learning with Momentum Distillation cites Learning Transferable Visual Models From Natural Language Supervision
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation cites Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation cites Learning Transferable Visual Models From Natural Language Supervision
- SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning cites Learning Transferable Visual Models From Natural Language Supervision
- SUA: Stealthy Multimodal Large Language Model Unlearning Attack cites Learning Transferable Visual Models From Natural Language Supervision
- Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models cites Learning Transferable Visual Models From Natural Language Supervision
Cited by top-tier papers8
- SineProject: Machine Unlearning for Stable Vision-Language AlignmentArpit Garg, Hemanth Saratchandran, Simon LuceyCVPR 2026 · 2 citations
- Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language ModelsKunhao Li, Wenhao Li, Di Wu, Lei Yang et al.AAAI 2026 · 2 citations
- VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language ModelsYili Wang, Lu Dai, Tairan Huang, Yijie Xu et al.CVPR 2026
- SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM UnlearningJiaqi Li, Zhijing Zhang, Jiahui Geng, Sheng Bi et al.ACL 2026
- SUA: Stealthy Multimodal Large Language Model Unlearning AttackXianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang et al.EMNLP 2025
Builds on31
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
- Align before Fuse: Vision and Language Representation Learning with Momentum DistillationJunnan Li, Ramprasaath R. Selvaraju, Akhilesh Gotmare, Shafiq R. Joty et al.NeurIPS 2021 · 2,985 citations
Related papers
- Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language ModelsZheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang et al.ACL 2025
- ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language ModelsYujie Lin, Chengyi Yang, Zhishang Xiang, YIPING SONG et al.ICML 2026
- Rethinking Post-Unlearning Behavior of Large Vision-Language ModelsMinsung Kim, Nakyeong Yang, Kyomin JungACL Findings 2026
- Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language ModelsJiaqi Li, Zihan You, Ruoyan Shen, Shenyu Zhang et al.ICLR 2026
- AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language ModelsHaokun Chen, Jianing Li, Yao Zhang, Jinhe Bi et al.AAAI 2026
