Exploring Hate Speech Detection in Multimodal Publications
Not on the map. Why?
Abstract (arXiv)
In this work we target the problem of hate speech detection in multimodal publications formed by a text and an image. We gather and annotate a large scale dataset from Twitter, MMHS150K, and propose different models that jointly analyze textual and visual information for hate speech detection, comparing them with unimodal detection. We provide quantitative and qualitative results and analyze the challenges of the proposed task. We find that, even though images are useful for the hate speech detection task, current multimodal models cannot outperform models analyzing only text. We discuss why and open the field and the dataset for further research.
Key facts. Cited by 103 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Oct 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 12; 2023: 17; 2024: 24; 2025: 16; 2026: 18.
103 papers.
Sort:
By area:
- 2022Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionalitycited by 529
- 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 155
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
- 2021A Survey on Multimodal Disinformation Detectioncited by 47
- 2021Disentangling Hate in Online Memescited by 46
- 2023HateMM: A Multi-Modal Dataset for Hate Video Classificationcited by 42
- 2022On Explaining Multimodal Hateful Meme Detection Modelscited by 29
- 2021The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stresscited by 27
- 2021A systematic review of Hate Speech automatic detection using Natural Language Processingcited by 27
- 2024Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Modelscited by 26
- 2021The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvementscited by 22
38 more
- 2021"Subverting the Jewtocracy": Online Antisemitism Detection Using Multimodal Deep Learningcited by 21
- 2022DISARM: Detecting the Victims Targeted by Harmful Memescited by 20
- 2023BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classificationcited by 18
- 2023LAraBench: Benchmarking Arabic AI with Large Language Modelscited by 16
- 2022Multimodal Hate Speech Detection from Bengali Memes and Textscited by 15
- 2023Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?cited by 14
- 2022Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defensecited by 13
- 2024Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanationscited by 13
- 2024Towards Comprehensive Detection of Chinese Harmful Memescited by 13
- 2021Exploring Visual Engagement Signals for Representation Learningcited by 12
- 2023Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memescited by 12
- 2024SoMeLVLM: A Large Vision Language Model for Social Media Processingcited by 11
- 2024Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretationscited by 10
- 2024ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videoscited by 10
- 2024BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Banglacited by 10
- 2021Multimodal Fusion Refiner Networkscited by 9
- 2023Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modalitycited by 9
- 2025Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Contentcited by 9
- 2021Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hatecited by 8
- 2021Revisiting Contextual Toxicity Detection in Conversationscited by 8
- 2025Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusioncited by 8
- 2024Deciphering Hate: Identifying Hateful Memes and Their Targetscited by 7
- 2024Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Modelscited by 7
- 2023CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wildcited by 6
- 2026MemeLens: Multilingual Multitask VLMs for Memescited by 6
- 2021Exploring multi-task multi-lingual learning of transformer models for hate speech and offensive speech identification in social mediacited by 5
- 2021Volta at SemEval-2021 Task 6: Towards Detecting Persuasive Texts and Images using Textual and Multimodal Ensemblecited by 5
- 2022BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformercited by 5
- 2024Neural Multimodal Topic Modeling: A Comprehensive Evaluationcited by 5
- 2024ArMeme: Propagandistic Content in Arabic Memescited by 5
- 2025The Impact of Persona-based Political Perspectives on Hateful Content Detectioncited by 5
- 2025MM-HSD: Multi-Modal Hate Speech Detection in Videoscited by 5
- 2021TweetBLM: A Hate Speech Dataset and Analysis of Black Lives Matter-related Microblogs on Twittercited by 4
- 2022TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memescited by 4
- 2024Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detectioncited by 4
- 2024SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memescited by 4
- 2025A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehensioncited by 4
- 2024GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?cited by 3
50 most cited of 103 All 103 (JSON)
- 2026Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection16 Sep 2026
- 2026SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection12 Sep 2026
- 2026Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy19 Aug 2026
- 2026COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models18 Aug 2026
- 2026HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection17 Jul 2026
- 2026PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media16 May 2026
- 2026Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts28 Apr 2026
- 2026Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection12 Apr 2026
- 2026Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach8 Apr 2026
- 2026More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection22 Mar 2026
- 2026Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking20 Mar 2026
- 2026Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation15 Mar 2026
38 more
- 2026Feature-level Interaction Explanations in Multimodal Transformers4 Mar 2026
- 2026Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework25 Feb 2026
- 2026Towards Training-free Multimodal Hate Localisation with Large Language Models10 Feb 2026
- 2026KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection29 Jan 2026
- 2026MemeLens: Multilingual Multitask VLMs for Memes18 Jan 2026
- 2026MEMEWEAVER: Inter-Meme Graph Reasoning for Sexism and Misogyny Detection13 Jan 2026
- 2025MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos11 Dec 2025
- 2025Ideology-Based LLMs for Content Moderation29 Oct 2025
- 2025DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images26 Sep 2025
- 2025MM-HSD: Multi-Modal Hate Speech Detection in Videos28 Aug 2025
- 2025A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehension22 Aug 2025
- 2025A Context-aware Attention and Graph Neural Network-based Multimodal Framework for Misogyny Detection7 Aug 2025
- 2025System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition24 Jul 2025
- 2025Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models29 Jun 2025
- 2025Web(er) of Hate: A Survey on How Hate Speech Is Typed19 Jun 2025
- 2025MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models22 May 2025
- 2025Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion17 May 2025
- 2025TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection24 Apr 2025
- 2025Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering23 Apr 2025
- 2025Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech13 Feb 2025
- 2025Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content11 Feb 2025
- 2025The Impact of Persona-based Political Perspectives on Hateful Content Detection1 Feb 2025
- 2024SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes29 Dec 2024
- 2024A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages28 Nov 2024
- 2024Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models6 Nov 2024
- 2024ProvocationProbe: Instigating Hate Speech Dataset from Twitter25 Oct 2024
- 2024BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla17 Oct 2024
- 2024Towards Comprehensive Detection of Chinese Harmful Memes3 Oct 2024
- 2024What is the social benefit of hate speech detection research? A Systematic Review26 Sep 2024
- 2024MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Framework8 Sep 2024
- 2024Multimodal Contrastive In-Context Learning23 Aug 2024
- 2024HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes11 Aug 2024
- 2024How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models29 Jun 2024
- 2024Empirical Evaluation of Public HateSpeech Datasets27 Jun 2024
- 2024ArMeme: Propagandistic Content in Arabic Memes6 Jun 2024
- 2024Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario31 May 2024
- 2024ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos31 May 2024
- 2024The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content17 May 2024
50 newest of 103 All 103 (JSON)
- 2024SoMeLVLM: A Large Vision Language Model for Social Media Processingcited by 11
- 2024Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretationscited by 10
- 2024Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Modelscited by 7
- 2025MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Modelscited by 1
- 2026COMIC: Reference-Aware Safety Gating for Multimodal Large Language Modelscited by 0
- 2026Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detectioncited by 0
- 2026Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection16 Sep 2026
- 2026COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models18 Aug 2026
- 2025MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models22 May 2025
- 2024Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models6 Nov 2024
- 2024SoMeLVLM: A Large Vision Language Model for Social Media Processing20 Feb 2024
- 2024Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations19 Feb 2024
- 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 155
- 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
- 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
- 2021A Survey on Multimodal Disinformation Detectioncited by 47
- 2021Disentangling Hate in Online Memescited by 46
- 2023HateMM: A Multi-Modal Dataset for Hate Video Classificationcited by 42
- 2022On Explaining Multimodal Hateful Meme Detection Modelscited by 29
- 2021The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stresscited by 27
- 2021A systematic review of Hate Speech automatic detection using Natural Language Processingcited by 27
- 2024Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Modelscited by 26
- 2021The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvementscited by 22
- 2021"Subverting the Jewtocracy": Online Antisemitism Detection Using Multimodal Deep Learningcited by 21
12 most cited of 92 All 92 (JSON)
- 2026SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection12 Sep 2026
- 2026Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy19 Aug 2026
- 2026HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection17 Jul 2026
- 2026PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media16 May 2026
- 2026Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts28 Apr 2026
- 2026Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach8 Apr 2026
- 2026More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection22 Mar 2026
- 2026Feature-level Interaction Explanations in Multimodal Transformers4 Mar 2026
- 2026Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework25 Feb 2026
- 2026Towards Training-free Multimodal Hate Localisation with Large Language Models10 Feb 2026
- 2026KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection29 Jan 2026
- 2026MemeLens: Multilingual Multitask VLMs for Memes18 Jan 2026
12 newest of 92 All 92 (JSON)