# SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes

arXiv: https://arxiv.org/abs/2412.20541 · HTML: https://mlsanity.com/paper/2412.20541/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 115 references that are in the map.
- First posted on arXiv 29 Dec 2024.

## Builds on (most cited first, 30 of 78)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)

## Built on by (most cited first, 4 of 4)

- [MemeIntel: Explainable Detection of Propagandistic and Hateful Memes](https://mlsanity.com/paper/2502.16612/) (2025)
- [SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection](https://mlsanity.com/paper/2509.16060/) (2025)
- [Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models](https://mlsanity.com/paper/2507.13761/) (2025)
- [Labels or Input? Rethinking Augmentation in Multimodal Hate Detection](https://mlsanity.com/paper/2508.11808/) (2025)

## Abstract (arXiv)

Memes act as cryptic tools for sharing sensitive ideas, often requiring contextual knowledge to interpret them correctly. It makes multimodal meme moderation difficult, as existing work either lacks high-quality datasets for nuanced hate categories or relies on low-quality social media visuals. Here, we curate two novel multimodal hate speech datasets comprising English memes - MHS and MHS-Con, which capture fine-grained hateful abstractions in regular and confounding scenarios, respectively. We benchmark these datasets against several competing baselines. Furthermore, we introduce SAFE-MEME (Structured reAsoning FramEwork) with its two variants: a novel multimodal Chain-of-Thought based framework employing Q&A-style reasoning (SAFE-MEME-QA) and a hierarchical categorization (SAFE-MEME-H) to enable robust hate speech detection in memes. SAFE-MEME-QA outperforms the strongest open-source baseline model, showing an improvement of 2% on MHS and 4.7% on MHS-Con and closely follows the closed-source models, GPT-4o and Gemini 2.5. In contrast, SAFE-MEME-H surpasses SAFE-MEME-QA, marking a 3% improvement over the best open-source baseline, while achieving performance comparable to GPT-4o only on MHS. We show that fine-tuning a single-layer adapter within SAFE-MEME-H outperforms fully fine-tuned models in regular fine-grained hateful meme detection. However, the fully fine-tuning approach with a Q&A setup is more effective for handling confounding cases. We also systematically examine the error cases, offering valuable insights into the robustness and limitations of the proposed structured reasoning framework for analyzing hateful memes.