3 papers
cs.CL2026
FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
Paramananda Bhaskar, Naquee Rizwan, Daksh Jogchand +2
Hateful meme detection remains a formidable challenge for vision-language models, as existing benchmarks are structurally observational - confounding rhetorical hate mechanisms wit…
cs.CL2026
See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation
Naquee Rizwan, Subhankar Swain, Paramananda Bhaskar +3
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 apply…
cs.CL2025
Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations
Naquee Rizwan, Paramananda Bhaskar, Mithun Das +3
There is a rapid increase in the use of multimedia content in current social media platforms. One of the highly popular forms of such multimedia content are memes. While memes have…