MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jha, Prince, Jain, Raghav, Mandal, Konika, Chadha, Aman, Saha, Sriparna, Bhattacharyya, Pushpak
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914829945536512
author Jha, Prince
Jain, Raghav
Mandal, Konika
Chadha, Aman
Saha, Sriparna
Bhattacharyya, Pushpak
author_facet Jha, Prince
Jain, Raghav
Mandal, Konika
Chadha, Aman
Saha, Sriparna
Bhattacharyya, Pushpak
contents In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with current research focusing mostly on text-based content, neglecting the widespread influence of multimodal content like memes. Addressing this gap, we present \textit{MemeGuard}, a comprehensive framework leveraging Large Language Models (LLMs) and Visual Language Models (VLMs) for meme intervention. \textit{MemeGuard} harnesses a specially fine-tuned VLM, \textit{VLMeme}, for meme interpretation, and a multimodal knowledge selection and ranking mechanism (\textit{MKS}) for distilling relevant knowledge. This knowledge is then employed by a general-purpose LLM to generate contextually appropriate interventions. Another key contribution of this work is the \textit{\textbf{I}ntervening} \textit{\textbf{C}yberbullying in \textbf{M}ultimodal \textbf{M}emes (ICMM)} dataset, a high-quality, labeled dataset featuring toxic memes and their corresponding human-annotated interventions. We leverage \textit{ICMM} to test \textit{MemeGuard}, demonstrating its proficiency in generating relevant and effective responses to toxic memes.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05344
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
Jha, Prince
Jain, Raghav
Mandal, Konika
Chadha, Aman
Saha, Sriparna
Bhattacharyya, Pushpak
Computation and Language
In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with current research focusing mostly on text-based content, neglecting the widespread influence of multimodal content like memes. Addressing this gap, we present \textit{MemeGuard}, a comprehensive framework leveraging Large Language Models (LLMs) and Visual Language Models (VLMs) for meme intervention. \textit{MemeGuard} harnesses a specially fine-tuned VLM, \textit{VLMeme}, for meme interpretation, and a multimodal knowledge selection and ranking mechanism (\textit{MKS}) for distilling relevant knowledge. This knowledge is then employed by a general-purpose LLM to generate contextually appropriate interventions. Another key contribution of this work is the \textit{\textbf{I}ntervening} \textit{\textbf{C}yberbullying in \textbf{M}ultimodal \textbf{M}emes (ICMM)} dataset, a high-quality, labeled dataset featuring toxic memes and their corresponding human-annotated interventions. We leverage \textit{ICMM} to test \textit{MemeGuard}, demonstrating its proficiency in generating relevant and effective responses to toxic memes.
title MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
topic Computation and Language
url https://arxiv.org/abs/2406.05344