See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation
This addresses the problem of scalable and cost-effective content moderation for social media platforms, though it is incremental in integrating detection, explanation, and intervention.
The paper tackles hateful meme moderation by proposing a framework that detects, explains, and intervenes in memes using generative AI models, achieving generalizable performance under limited data conditions with few-shot adaptability.
In this work, we examine hateful memes from three complementary angles - how to detect them, how to explain their content and how to intervene them prior to being posted - by applying a range of strategies built on top of generative AI models. To the best of our knowledge, explanation and intervention have typically been studied separately from detection, which does not reflect real-world conditions. Further, since curating large annotated datasets for meme moderation is prohibitively expensive, we propose a novel framework that leverages task-specific generative multimodal agents and the few-shot adaptability of large multimodal models to cater to different types of memes. We believe this is the first work focused on generalizable hateful meme moderation under limited data conditions, and has strong potential for deployment in real-world production scenarios. Warning: Contains potentially toxic contents.