Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
This addresses privacy concerns in MLLMs for users and developers, though it is incremental as it builds on existing unlearning methods.
The paper tackles the problem of multimodal large language models (MLLMs) inadvertently memorizing privacy-sensitive information by proposing the Sculpted Memory Forgetting Adapter (SMFA) to achieve precise unlearning without degrading general image understanding, as validated through extensive experiments.
Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting because they often degrade the model's general image understanding performance. To address this, we propose the Sculpted Memory Forgetting Adapter (SMFA), which confines forgetting to targeted memory regions while preserving overall capabilities. SMFA first fine-tunes the model to replace sensitive responses with refusals, yielding a memory forgetting adapter, and then applies a retaining anchor-guided masking mechanism to prevent interference with unrelated knowledge and understanding ability. To systematically evaluate selective MLLM unlearning, we introduce S-MLLMUn Bench, the first benchmark designed to jointly assess the removal of sensitive knowledge and retention of general visual understanding. Extensive experiments show that, unlike prior methods, SMFA achieves precise and controllable unlearning while maintaining the model's foundational image understanding.