Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

TL;DR

This paper introduces MIP-Editor, a novel method for effective multimodal unlearning in large language models that selectively forget sensitive information across modalities while maintaining overall performance.

Contribution

It proposes a modality-specific attribution and influential neuron path editing approach to improve consistency and effectiveness of unlearning in multimodal models.

Findings

Achieves up to 87.75% forgetting rate on multimodal tasks.

Improves general knowledge retention by up to 54.26%.

Preserves 77.9% of performance on textual tasks.

Abstract

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity mitigation, and intellectual property violations. Machine Unlearning (MU) offers a practical solution by selectively forgetting targeted knowledge while preserving overall model utility. When applied to MLLMs, existing neuron-editing-based MU approaches face two fundamental challenges: (1) forgetting becomes inconsistent across modalities because existing point-wise attribution methods fail to capture the structured, layer-by-layer information flow that connects different modalities; and (2) general knowledge performance declines when sensitive neurons that also support important reasoning paths are pruned, as this disrupts the model's ability to generalize. To alleviate these limitations, we propose a multimodal influential neuron path editor (MIP-Editor) for MU. Our approach introduces modality-specific attribution scores to identify influential neuron paths responsible for encoding forget-set knowledge and applies influential-path-aware neuron-editing via representation misdirection. This strategy also enables effective and coordinated forgetting across modalities while preserving the model's general capabilities. Experimental results demonstrate that MIP-Editor achieves a superior unlearning performance on multimodal tasks, with a maximum forgetting rate of 87.75% and up to 54.26% improvement in general knowledge retention. On textual tasks, MIP-Editor achieves up to 80.65% forgetting and preserves 77.9% of general performance. Codes are available at https://github.com/PreckLi/MIP-Editor.