Challenge: Existing models for multimodal hate detection lack implicit hateful cues, cross-modal-induced hate, and diversity of hate target groups.
Approach: They propose a hypergraph-based prompting fusion model that uses LLMs to generate hate cue prompts and hypergraph learning to merge multimodal hate features.
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets showing that it can detect hate content across multiple modalities.

Similar Papers

HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for hateful video detection rely on unimodal analysis or feature fusion . Existing tools struggle to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor .
Approach: They propose a reasoning-based hateful video detection framework with multimodal large language models . they integrate Chain-of-Thought reasoning to enhance multimodal interaction modeling .
Outcome: The proposed framework outperforms existing tools on two public datasets covering English and Chinese.
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate (2021.findings-acl)

Copied to clipboard

Challenge: Imlicit hate content has unusual syntax, polysemic words, and fewer markers of prejudice, e.g., slurs . multimodal content is harder to detect than unimodal content, such as memes .
Approach: They evaluate the role of semantic and multimodal context for detecting implicit and explicit hate . they find that all models perform better on content with full annotator agreement .
Outcome: The proposed model outperforms other models on implicit and explicit hate detection tasks because of its lower propensity towards false positives.
DGLF: A Dual Graph-based Learning Framework for Multi-modal Sarcasm Detection (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for multimodal sarcasm detection neglect high-order relationships and underestimate high-frequency messages.
Approach: They propose a Dual Graph-based Learning Framework to capture inter-modal inconsistencies . they propose combining a hypergraph and a vanilla graph to achieve enhanced propagation .
Outcome: The proposed model outperforms existing state-of-the-art methods on two benchmark datasets.
Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection (2024.eacl-srw)

Copied to clipboard

Challenge: Existing approaches to multimodal hateful content detection focus on detecting hate speech from text-based content, but they fail to address modality-specific features.
Approach: They propose a context-aware attention framework for multimodal hateful content detection that integrates an attention layer to meaningfully align the visual and textual features.
Outcome: The proposed framework achieves F1-scores of 69.7% and 70.3% on two hateful meme datasets and shows 2.5% and 3.2% performance improvement over the state-of-the-art systems.
More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing systems struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities.
Approach: They propose a framework to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion.
Outcome: The proposed framework outperforms state-of-the-art benchmarks on H-VLI and on established benchmarks.
Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Recent research has developed models targeting specific modalities but lacks transferability between formats.
Approach: They conduct extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities.
Outcome: The proposed model outperforms vision-language demonstrations in few-shot learning settings.
Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for detecting hateful memes rely on extensive training.
Approach: They propose a method that integrates evolution attribute and in-context information of memes into large multimodal models via Chain-of-Evolution (CoE) prompting.
Outcome: The proposed method improves existing methods on public datasets and can be used as interpretive tool to promote understanding of evolution of memes.
Modular and Parameter-Efficient Multimodal Fusion with Prompting (2022.findings-acl)

Copied to clipboard

Challenge: Recent research has made impressive progress in large-scale multimodal pre-training.
Approach: They propose to use prompt vectors to align multimodal modalities by pretraining text inputs with prompts or embedding vectors.
Outcome: The proposed method achieves comparable performance to several other multimodal fusion methods in low-resource settings.
AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection (2025.emnlp-main)

Copied to clipboard

Challenge: Current approaches to detect hate speech rely on contrastive learning to distinguish hate from non-hate sentences.
Approach: They propose a novel approach to detect implicit hate speech by identifying explicit targets . they use a pretrained Named Entity Recognition model to capture explicit target information .
Outcome: The proposed approach outperforms current methods and achieves faster convergence.
TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalities (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing multimodal rumor detection methods focus on learning joint modality representations from complete multimodal training data, rendering them ineffective in addressing the common occurrence of missing modalities in real-world scenarios.
Approach: They propose a hierarchical soft prompt model TriSPrompt which integrates three types of prompts to effectively detect rumors in incomplete multimodal data.
Outcome: The proposed model achieves an accuracy gain of over 13% compared to state-of-the-art models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations