SyncAI.news, a Varaisys broadcasting
PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation
NR

Naquee Rizwan, Subhankar Swain, Paramananda Bhaskar, Shehryaar Shah Khan, Gagan Aryan, Animesh Mukherjee

· 1 min read

ResearcharXiv cs.CL

PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation

arXiv:2601.04692v2 Announce Type: replace Abstract: 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 before 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 - PEST - that leverages task-specific generative VLMs and the few-shot adaptability of large VLMs 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.

Original source

This story was published by arXiv cs.CL and written by Naquee Rizwan, Subhankar Swain, Paramananda Bhaskar, Shehryaar Shah Khan, Gagan Aryan, Animesh Mukherjee. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News