I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition

我懂你的梗，哪怕它今天才出现：通过开放世界知识获取理解不断演变的模因

Abstract: Multimodal memes are dynamic and often require up to date background knowledge for interpretation. Existing methods often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes. 摘要： 多模态模因（Meme）具有动态性，通常需要最新的背景知识才能进行解读。现有的方法往往忽视了这些知识，或者依赖于预训练模型中固定的参数化知识，而这些知识对于新兴模因来说可能是不完整、过时或无法获取的。

We introduce Query Retrieve Conclude, a zero shot framework that identifies missing knowledge, retrieves open web evidence, and synthesizes evidence grounded background knowledge for meme understanding and detection. 我们引入了“查询-检索-总结”（Query Retrieve Conclude）这一零样本框架，它能够识别缺失的知识，检索开放网络证据，并综合基于证据的背景知识，从而实现对模因的理解与检测。

We also introduce a curated meme understanding benchmark of recent memes from 2024 to 2026 with external background knowledge annotations. 我们还推出了一个精心策划的模因理解基准测试，涵盖了 2024 年至 2026 年间的近期模因，并附带了外部背景知识标注。

Experiments on three meme understanding datasets and five meme detection tasks show that our framework improves knowledge recovery, meme understanding and downstream detection over zero shot baselines. 在三个模因理解数据集和五个模因检测任务上的实验表明，与零样本基准相比，我们的框架在知识恢复、模因理解和下游检测方面均有显著提升。