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

2026-06-03

AI Summary

This work addresses the limitations of existing methods in understanding dynamic multimodal memes, which often rely on fixed, outdated, or incomplete background knowledge embedded in pretrained models. To overcome this, we propose a Query-Retrieve-Conclude zero-shot framework that dynamically interprets emerging memes by identifying knowledge gaps, retrieving relevant evidence from the open web, and synthesizing multimodal contextual knowledge. We introduce the first benchmark tailored to emerging memes from 2024–2026, incorporating an open-world knowledge acquisition mechanism that transcends static knowledge constraints. Experimental results demonstrate that our approach significantly outperforms zero-shot baselines across three comprehension datasets and five detection tasks, achieving substantial improvements in knowledge recovery rate, interpretation accuracy, and downstream detection performance.

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often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes. 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. We also introduce a curated meme understanding benchmark of recent memes from 2024 to 2026 with external background knowledge annotations. 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.

Problem

• memes
• background knowledge
• open-world knowledge
• multimodal understanding
• emerging content

Innovation

• zero-shot learning
• open-world knowledge acquisition
• multimodal memes
• knowledge retrieval
• meme understanding