Can We Edit Multimodal Large Language Models?
This work addresses the problem of model editing for multimodal AI systems, which is incremental as it builds on existing single-modal editing methods by extending them to a new, more complex domain.
The paper tackles the problem of editing Multimodal Large Language Models (MLLMs), which is more challenging than editing single-modal LLMs, by constructing a new benchmark called MMEdit with innovative metrics for evaluation. The result shows that previous baselines can edit MLLMs to some extent but with barely satisfactory effects, indicating the task's difficulty.
In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the editing process. To facilitate research in this area, we construct a new benchmark, dubbed MMEdit, for editing multimodal LLMs and establishing a suite of innovative metrics for evaluation. We conduct comprehensive experiments involving various model editing baselines and analyze the impact of editing different components for multimodal LLMs. Empirically, we notice that previous baselines can implement editing multimodal LLMs to some extent, but the effect is still barely satisfactory, indicating the potential difficulty of this task. We hope that our work can provide the NLP community with insights. Code and dataset are available in https://github.com/zjunlp/EasyEdit.