arXiv 2510.225352026-01-03cs.AIcs.CL

OFFSIDE: 多模态大语言模型中误信信息消除的基准测试

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models

Harbin Institute of Technology（哈尔滨工业大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；BIAI, ZJUT & D5Data.ai（BIAI、浙江工业大学及D5Data.ai）；National University of Singapore（新加坡国立大学）

Hao Zheng, Zirui Pang, Ling li, Zhijie Deng, Yuhan Pu, Zhaowei Zhu, Xiaobo Xia, Jiaheng Wei

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

OFFSIDE通过足球转会谣言数据集，评估多模态大语言模型中误信信息消除的挑战与方法，揭示现有技术的局限性。

摘要：

多模态大语言模型（MLLMs）的发展加剧了数据隐私方面的担忧，使机器消除（MU），即选择性地移除已学习的信息，成为一项关键需求。然而，现有的MLLMs消除基准测试受限于图像多样性不足、潜在的不准确性以及评估场景的不足，无法捕捉到现实应用中的复杂性。为了促进MLLMs消除的发展并缓解上述限制，我们引入OFFSIDE，一种基于足球转会谣言的新型基准测试，用于评估MLLMs中的误信信息消除。该人工整理的数据库包含15680条记录，涵盖80名球员，提供了一个包含四个测试集的全面框架，以评估遗忘效果、泛化能力、实用性以及鲁棒性。OFFSIDE支持高级设置，如选择性消除和纠正再学习，并且关键的是，支持单模态消除（仅消除文本数据）。我们对多种基线的广泛评估揭示了关键发现：（1）单模态方法（消除基于文本的知识）在多模态谣言上失败；（2）消除效果主要由灾难性遗忘驱动；（3）所有方法在“视觉谣言”（谣言出现在图像中）上挣扎；（4）被消除的谣言可以轻易恢复，并且（5）所有方法都容易受到提示攻击。这些结果暴露了当前方法中的显著漏洞，突显了对更鲁棒的多模态消除解决方案的需求。代码可在https://github.com/zh121800/OFFSIDE上获得。

英文摘要：

Advances in Multimodal Large Language Models (MLLMs) intensify concerns about data privacy, making Machine Unlearning (MU), the selective removal of learned information, a critical necessity. However, existing MU benchmarks for MLLMs are limited by a lack of image diversity, potential inaccuracies, and insufficient evaluation scenarios, which fail to capture the complexity of real-world applications. To facilitate the development of MLLMs unlearning and alleviate the aforementioned limitations, we introduce OFFSIDE, a novel benchmark for evaluating misinformation unlearning in MLLMs based on football transfer rumors. This manually curated dataset contains 15.68K records for 80 players, providing a comprehensive framework with four test sets to assess forgetting efficacy, generalization, utility, and robustness. OFFSIDE supports advanced settings like selective unlearning and corrective relearning, and crucially, unimodal unlearning (forgetting only text data). Our extensive evaluation of multiple baselines reveals key findings: (1) Unimodal methods (erasing text-based knowledge) fail on multimodal rumors; (2) Unlearning efficacy is largely driven by catastrophic forgetting; (3) All methods struggle with "visual rumors" (rumors appear in the image); (4) The unlearned rumors can be easily recovered and (5) All methods are vulnerable to prompt attacks. These results expose significant vulnerabilities in current approaches, highlighting the need for more robust multimodal unlearning solutions. The code is available at https://github.com/zh121800/OFFSIDE

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。