# MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes

arXiv: https://arxiv.org/abs/2607.27798 · HTML: https://mlsanity.com/paper/2607.27798/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [MMSearch-R1: Incentivizing LMMs to Search](https://mlsanity.com/paper/2506.20670/) (2025)
- [Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories](https://mlsanity.com/paper/2306.09224/) (2023)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists](https://mlsanity.com/paper/2403.18771/) (2024)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs](https://mlsanity.com/paper/2404.15406/) (2024)
- [SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge](https://mlsanity.com/paper/2405.14554/) (2024)
- [Can MLLMs Understand the Deep Implication Behind Chinese Images?](https://mlsanity.com/paper/2410.13854/) (2024)
- [Towards Comprehensive Detection of Chinese Harmful Memes](https://mlsanity.com/paper/2410.02378/) (2024)
- [D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning -- A Benchmark Dataset and Method](https://mlsanity.com/paper/2509.06771/) (2025)
- [MemeLens: Multilingual Multitask VLMs for Memes](https://mlsanity.com/paper/2601.12539/) (2026)
- [AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking](https://mlsanity.com/paper/2601.17645/) (2026)
- [M-QUEST -- Meme Question-Understanding Evaluation on Semantics and Toxicity](https://mlsanity.com/paper/2603.03315/) (2026)
- [I Came, I Saw, I Explained: Benchmarking Multimodal LLMs on Figurative Meaning in Memes](https://mlsanity.com/paper/2603.23229/) (2026)

## Built on by (most cited first, 1 of 1)

- [MemeMind: Reference-Guided Trace Construction for Offline Context Optimization](https://mlsanity.com/paper/2608.09316/) (2026)

## Abstract (arXiv)

Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels. Memes expose this gap because they rely on cultural entities, background knowledge, and community conventions. Most meme benchmarks reduce interpretation to labels or holistic scores, obscuring where an explanation breaks down. We introduce MemeBench, a diagnostic benchmark of 1,253 Chinese and English memes with human-written references and quality-controlled VIKR annotations, centered on anime, comics, games, and adjacent online subcultures. Its VIKR schema decomposes explanations into Visual clues, Identity links, Knowledge units, and Reasoning mechanisms. Across 26 LVLMs, every model covers visible content more reliably than the knowledge needed to interpret it, and even the strongest retains a 22.6% Visual-Knowledge gap. To test whether this diagnosis can guide improvement, we introduce KAR, an entity-guided retrieval baseline built on CultureBase. Across four controlled models, KAR raises VIKR Success by 3.6-7.4% and, compared with generic retrieval, repairs more answers and breaks fewer. Yet both retrieval conditions improve Identity and Knowledge while reducing Visual coverage in every comparison. MemeBench reveals whether an interpretation succeeds, what is missing, and whether targeted evidence fills the diagnosed gap.