See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911360554631168 |
|---|---|
| author | Rizwan, Naquee Swain, Subhankar Bhaskar, Paramananda Aryan, Gagan Khan, Shehryaar Shah Mukherjee, Animesh |
| author_facet | Rizwan, Naquee Swain, Subhankar Bhaskar, Paramananda Aryan, Gagan Khan, Shehryaar Shah Mukherjee, Animesh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04692 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation Rizwan, Naquee Swain, Subhankar Bhaskar, Paramananda Aryan, Gagan Khan, Shehryaar Shah Mukherjee, Animesh Computation and Language Computer Vision and Pattern Recognition 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. |
| title | See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.04692 |