# From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection

arXiv: https://arxiv.org/abs/2602.07497 · HTML: https://mlsanity.com/paper/2602.07497/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis](https://mlsanity.com/paper/2308.16705/) (2023)
- [CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries](https://mlsanity.com/paper/2501.01282/) (2025)
- [A Multilingual View of Unsupervised Machine Translation](https://mlsanity.com/paper/2002.02955/) (2020)
- [See It from My Perspective: How Language Affects Cultural Bias in Image Understanding](https://mlsanity.com/paper/2406.11665/) (2024)
- [Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs](https://mlsanity.com/paper/2409.07246/) (2024)
- [Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models](https://mlsanity.com/paper/2411.03888/) (2024)

## Built on by (most cited first, 2 of 2)

- [UNIVID: Unified Vision-Language Model for Video Moderation](https://mlsanity.com/paper/2606.05748/) (2026)
- [AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes](https://mlsanity.com/paper/2607.27393/) (2026)

## Abstract (arXiv)

Cultural context profoundly shapes how people interpret online content, yet vision-language models (VLMs) remain predominantly trained through Western or English-centric lenses. This limits their fairness and cross-cultural robustness in tasks like hateful meme detection. We introduce a systematic evaluation framework designed to diagnose and quantify the cross-cultural robustness of state-of-the-art VLMs across multilingual meme datasets, analyzing three axes: (i) learning strategy (zero-shot vs. one-shot), (ii) prompting language (native vs. English), and (iii) translation effects on meaning and detection. Results show that the common ``translate-then-detect'' approach deteriorate performance, while culturally aligned interventions - native-language prompting and one-shot learning - significantly enhance detection. Our findings reveal systematic convergence toward Western safety norms and provide actionable strategies to mitigate such bias, guiding the design of globally robust multimodal moderation systems.