Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering
This addresses the challenge of identifying subtle hate speech in memes for social media moderation, though it appears incremental as it builds on existing multimodal detection methods.
The paper tackles the problem of detecting hateful content in memes, which evades traditional unimodal systems due to their multimodal nature, by proposing a framework that integrates OCR, captioning, sub-label classification, RAG, and VQA, achieving improved accuracy and AUC-ROC on the Facebook Hateful Memes dataset.
Memes are widely used for humor and cultural commentary, but they are increasingly exploited to spread hateful content. Due to their multimodal nature, hateful memes often evade traditional text-only or image-only detection systems, particularly when they employ subtle or coded references. To address these challenges, we propose a multimodal hate detection framework that integrates key components: OCR to extract embedded text, captioning to describe visual content neutrally, sub-label classification for granular categorization of hateful content, RAG for contextually relevant retrieval, and VQA for iterative analysis of symbolic and contextual cues. This enables the framework to uncover latent signals that simpler pipelines fail to detect. Experimental results on the Facebook Hateful Memes dataset reveal that the proposed framework exceeds the performance of unimodal and conventional multimodal models in both accuracy and AUC-ROC.