# MemeIntel: Explainable Detection of Propagandistic and Hateful Memes

arXiv: https://arxiv.org/abs/2502.16612 · HTML: https://mlsanity.com/paper/2502.16612/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 77 references that are in the map.
- First posted on arXiv 23 Feb 2025.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Detecting and Understanding Harmful Memes: A Survey](https://mlsanity.com/paper/2205.04274/) (2022)
- [Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features](https://mlsanity.com/paper/2210.05916/) (2022)
- [Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge](https://mlsanity.com/paper/2012.12975/) (2020)
- [SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images](https://mlsanity.com/paper/2105.09284/) (2021)
- [Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection](https://mlsanity.com/paper/2308.08088/) (2023)
- [Evaluating GPT-3 Generated Explanations for Hateful Content Moderation](https://mlsanity.com/paper/2305.17680/) (2023)
- [Pre-Training BERT on Arabic Tweets: Practical Considerations](https://mlsanity.com/paper/2102.10684/) (2021)
- [Decoding the Underlying Meaning of Multimodal Hateful Memes](https://mlsanity.com/paper/2305.17678/) (2023)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [Argotario: Computational Argumentation Meets Serious Games](https://mlsanity.com/paper/1707.06002/) (2017)
- [NativQA: Multilingual Culturally-Aligned Natural Query for LLMs](https://mlsanity.com/paper/2407.09823/) (2024)
- [On Explaining Multimodal Hateful Meme Detection Models](https://mlsanity.com/paper/2204.01734/) (2022)
- [Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech](https://mlsanity.com/paper/2209.04889/) (2022)

## Built on by (most cited first, 10 of 10)

- [ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection](https://mlsanity.com/paper/2510.08630/) (2025)
- [MemeLens: Multilingual Multitask VLMs for Memes](https://mlsanity.com/paper/2601.12539/) (2026)
- [PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation](https://mlsanity.com/paper/2601.04692/) (2026)
- [Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation](https://mlsanity.com/paper/2604.05083/) (2026)
- [AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes](https://mlsanity.com/paper/2607.27393/) (2026)
- [HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes](https://mlsanity.com/paper/2608.16622/) (2026)
- [Why Current XAI Is Not Enough for Arabic NLP: A Critical Survey of the Explainability Gap](https://mlsanity.com/paper/2608.26144/) (2026)
- [Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection](https://mlsanity.com/paper/2609.18860/) (2026)
- [ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts](https://mlsanity.com/paper/2609.29349/) (2026)
- [UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes](https://mlsanity.com/paper/2610.13783/) (2026)

## Abstract (arXiv)

The proliferation of multimodal content on social media presents significant challenges in understanding and moderating complex, context-dependent issues such as misinformation, hate speech, and propaganda. While efforts have been made to develop resources and propose new methods for automatic detection, limited attention has been given to jointly modeling label detection and the generation of explanation-based rationales, which often leads to degraded classification performance when trained simultaneously. To address this challenge, we introduce MemeXplain, an explanation-enhanced dataset for propagandistic memes in Arabic and hateful memes in English, making it the first large-scale resource for these tasks. To solve these tasks, we propose a multi-stage optimization approach and train Vision-Language Models (VLMs). Our results show that this strategy significantly improves both label detection and explanation generation quality over the base model, outperforming the current state-of-the-art with an absolute improvement of ~1.4% (Acc) on ArMeme and ~2.2% (Acc) on Hateful Memes. For reproducibility and future research, we aim to make the MemeXplain dataset and scripts publicly available (https://github.com/MohamedBayan/MemeIntel).