提出首个多模态大模型持续遗忘评估基准，揭示遗忘导致模型性能持续下降的难题。
MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
- 构建包含127个实体的长期遗忘测试集，覆盖9类多模态数据
- 发现现有方法在持续遗忘下出现严重累积性能退化
- 提出LUMoE方法，有效保持多模态对齐，适合需长期数据清理的场景
多模态大语言模型（MLLM）基于海量多模态数据训练，当数据所有者要求移除特定内容时，数据遗忘变得日益重要。现实中，这类请求常随时间顺序出现，形成多模态大模型持续遗忘的挑战性问题。然而，现有基准在规模和范围上均有限，难以捕捉该问题的复杂性。为此，我们引入了MLUBench，一个大规模、全面的基准，涵盖9类共127个实体，在持续遗忘请求下进行评估。通过广泛实验，我们发现现有遗忘方法存在严重的累积性能退化。更关键的是，我们识别出独特挑战：与单模态模型不同，MLLM的持续遗忘受限于多模态对齐的维持；持续从一模态中遗忘会损害整个模型。为缓解此问题，我们提出LUMoE方法，实验表明其显著减轻了基线方法面临的退化问题。源代码与数据集已在https://github.com/lihe-maxsize/Lifelong_Unlearning_main公开。
原文摘要 · Abstract (English)
Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。