# On Explaining Multimodal Hateful Meme Detection Models

arXiv: https://arxiv.org/abs/2204.01734 · HTML: https://mlsanity.com/paper/2204.01734/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 36 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2005.07310/) (2020)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2110.00413/) (2021)
- [Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers](https://mlsanity.com/paper/2109.04448/) (2021)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge](https://mlsanity.com/paper/2012.12975/) (2020)
- [A Multimodal Framework for the Detection of Hateful Memes](https://mlsanity.com/paper/2012.12871/) (2020)
- [Disentangling Hate in Online Memes](https://mlsanity.com/paper/2108.06207/) (2021)
- [Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution](https://mlsanity.com/paper/2012.08290/) (2020)
- [Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations](https://mlsanity.com/paper/2001.05495/) (2020)
- [Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks](https://mlsanity.com/paper/2012.12352/) (2020)
- [Multimodal Learning for Hateful Memes Detection](https://mlsanity.com/paper/2011.12870/) (2020)
- [Towards Transparent AI Systems: Interpreting Visual Question Answering Models](https://mlsanity.com/paper/1608.08974/) (2016)

## Built on by (most cited first, 29 of 29)

- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection](https://mlsanity.com/paper/2308.08088/) (2023)
- [Decoding the Underlying Meaning of Multimodal Hateful Memes](https://mlsanity.com/paper/2305.17678/) (2023)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [Towards Low-Resource Harmful Meme Detection with LMM Agents](https://mlsanity.com/paper/2411.05383/) (2024)
- [Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models](https://mlsanity.com/paper/2401.13298/) (2024)
- [MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection](https://mlsanity.com/paper/2507.06908/) (2025)
- [Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions](https://mlsanity.com/paper/2502.11073/) (2025)
- [Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations](https://mlsanity.com/paper/2401.09899/) (2024)
- [Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities](https://mlsanity.com/paper/2406.07353/) (2024)
- [Towards Comprehensive Detection of Chinese Harmful Memes](https://mlsanity.com/paper/2410.02378/) (2024)
- [TotalDefMeme: A Multi-Attribute Meme dataset on Total Defence in Singapore](https://mlsanity.com/paper/2305.17911/) (2023)
- [MemeIntel: Explainable Detection of Propagandistic and Hateful Memes](https://mlsanity.com/paper/2502.16612/) (2025)
- [MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation](https://mlsanity.com/paper/2403.14652/) (2024)
- [Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection](https://mlsanity.com/paper/2407.21004/) (2024)
- [HateProof: Are Hateful Meme Detection Systems really Robust?](https://mlsanity.com/paper/2302.05703/) (2023)
- [Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning](https://mlsanity.com/paper/2410.05600/) (2024)
- [PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models](https://mlsanity.com/paper/2312.06093/) (2023)
- [MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models](https://mlsanity.com/paper/2505.17433/) (2025)
- [From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment](https://mlsanity.com/paper/2506.18919/) (2025)
- [PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation](https://mlsanity.com/paper/2601.04692/) (2026)
- [Multimodal Contrastive In-Context Learning](https://mlsanity.com/paper/2408.12959/) (2024)
- [Follow Us and Become Famous! Insights and Guidelines From Instagram Engagement Mechanisms](https://mlsanity.com/paper/2301.06815/) (2023)
- [Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: a Case Study on Hateful Memes](https://mlsanity.com/paper/2308.11585/) (2023)
- [Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering](https://mlsanity.com/paper/2504.16723/) (2025)
- [All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction](https://mlsanity.com/paper/2601.04567/) (2026)
- [Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval](https://mlsanity.com/paper/2510.15946/) (2025)
- [Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes](https://mlsanity.com/paper/2607.15442/) (2026)
- [SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection](https://mlsanity.com/paper/2609.13794/) (2026)

## Abstract (arXiv)

Hateful meme detection is a new multimodal task that has gained significant traction in academic and industry research communities. Recently, researchers have applied pre-trained visual-linguistic models to perform the multimodal classification task, and some of these solutions have yielded promising results. However, what these visual-linguistic models learn for the hateful meme classification task remains unclear. For instance, it is unclear if these models are able to capture the derogatory or slurs references in multimodality (i.e., image and text) of the hateful memes. To fill this research gap, this paper propose three research questions to improve our understanding of these visual-linguistic models performing the hateful meme classification task. We found that the image modality contributes more to the hateful meme classification task, and the visual-linguistic models are able to perform visual-text slurs grounding to a certain extent. Our error analysis also shows that the visual-linguistic models have acquired biases, which resulted in false-positive predictions.