I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition
Not on the map. Why?
Abstract (arXiv)
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often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes.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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 3 Jun 2026.
Builds on
16 of 28 references.
References · 16
- 2019Language Models as Knowledge Bases?cited by 1,936
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
- 2024GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abusecited by 52
- 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 47
- 2021Disentangling Hate in Online Memescited by 46
- 2023MemeCap: A Dataset for Captioning and Interpreting Memescited by 46
- 2022What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memescited by 18
- 2024Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checkingcited by 18
- 2025AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Webcited by 18
- 2025MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detectioncited by 15
- 2024MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencingcited by 12
- 2025ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detectioncited by 8
4 more
- 2021Entropy and complexity unveil the landscape of memes evolutioncited by 4
- 2026PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderationcited by 4
- 2026Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detectioncited by 3
- 2026They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural Referencescited by 1
Built on by
Not cited yet.