Machine unlearning (MU) empowers individuals with the'right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to Multimodal Large Language Models (MLLMs), particularly in scenarios of forgetting the leaked visual data of concepts.

However, Is asingle comparison between superior and inferior responses sufficient for preference learning in MLLMs? Upon consideration, we find that a multi-level preference framework offers greater benefits for preference learning, primarily due to two main intuitive advantages.

As Large Language Models (LLMs) demonstrate impressive capabilities, demys-tifying their internal mechanisms becomes increasingly vital.

We hope our work will contribute to the development of general MLLMs suitable for web-based content generation and task automation.