MemeSense:一种面向社交常识驱动的模因审核的自适应上下文框架
MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
AI总结:
MemeSense是一个自适应上下文框架,结合视觉与文本理解及常识线索,检测模因中的隐性有害内容,在多个基准上显著优于现有方法。
摘要:
在线模因是一种强大但具有挑战性的内容审核媒介,常常将有害意图隐藏在幽默、讽刺或文化象征背后。传统审核系统,尤其是依赖显式文本的系统,往往无法识别此类微妙或隐性的伤害。我们提出了MemeSense,一个自适应框架,旨在通过结合视觉与文本理解,以及精选的、语义对齐的、富含常识线索的示例,为有害模因生成具有社会依据的干预措施。这使得模型能够检测细微的复杂威胁,如厌女、刻板印象或粗俗内容,即使模因缺乏明显的语言线索。在多个基准数据集上,MemeSense优于最先进的方法,在非文本模因上实现了高达35%的语义相似度提升和9%的BERTScore改进,并且在富含文本的模因上也取得了显著增益。这些结果凸显了MemeSense朝着更安全、更具上下文感知能力的AI系统迈出的有希望的一步,适用于现实世界的内容审核。代码和数据可在 https://github.com/sayantan11995/MemeSense 获取。
英文摘要:
Online memes are a powerful yet challenging medium for content moderation, often masking harmful intent behind humor, irony, or cultural symbolism. Conventional moderation systems "especially those relying on explicit text" frequently fail to recognize such subtle or implicit harm. We introduce MemeSense, an adaptive framework designed to generate socially grounded interventions for harmful memes by combining visual and textual understanding with curated, semantically aligned examples enriched with commonsense cues. This enables the model to detect nuanced complexed threats like misogyny, stereotyping, or vulgarity "even in memes lacking overt language". Across multiple benchmark datasets, MemeSense outperforms state-of-the-art methods, achieving up to 35% higher semantic similarity and 9% improvement in BERTScore for non-textual memes, and notable gains for text-rich memes as well. These results highlight MemeSense as a promising step toward safer, more context-aware AI systems for real-world content moderation. Code and data available at: https://github.com/sayantan11995/MemeSense
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。