Unpacking Hateful Memes: Presupposed Context and False Claims

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cai, Weibin, Li, Jiayu, Zafarani, Reza
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911203763159040
author Cai, Weibin
Li, Jiayu
Zafarani, Reza
author_facet Cai, Weibin
Li, Jiayu
Zafarani, Reza
contents While memes are often humorous, they are frequently used to disseminate hate, causing serious harm to individuals and society. Current approaches to hateful meme detection mainly rely on pre-trained language models. However, less focus has been dedicated to \textit{what make a meme hateful}. Drawing on insights from philosophy and psychology, we argue that hateful memes are characterized by two essential features: a \textbf{presupposed context} and the expression of \textbf{false claims}. To capture presupposed context, we develop \textbf{PCM} for modeling contextual information across modalities. To detect false claims, we introduce the \textbf{FACT} module, which integrates external knowledge and harnesses cross-modal reference graphs. By combining PCM and FACT, we introduce \textbf{\textsf{SHIELD}}, a hateful meme detection framework designed to capture the fundamental nature of hate. Extensive experiments show that SHIELD outperforms state-of-the-art methods across datasets and metrics, while demonstrating versatility on other tasks, such as fake news detection.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09935
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unpacking Hateful Memes: Presupposed Context and False Claims
Cai, Weibin
Li, Jiayu
Zafarani, Reza
Computation and Language
Artificial Intelligence
68T50, 68T45, 68T07
I.2.7; I.2.10; I.2.6
While memes are often humorous, they are frequently used to disseminate hate, causing serious harm to individuals and society. Current approaches to hateful meme detection mainly rely on pre-trained language models. However, less focus has been dedicated to \textit{what make a meme hateful}. Drawing on insights from philosophy and psychology, we argue that hateful memes are characterized by two essential features: a \textbf{presupposed context} and the expression of \textbf{false claims}. To capture presupposed context, we develop \textbf{PCM} for modeling contextual information across modalities. To detect false claims, we introduce the \textbf{FACT} module, which integrates external knowledge and harnesses cross-modal reference graphs. By combining PCM and FACT, we introduce \textbf{\textsf{SHIELD}}, a hateful meme detection framework designed to capture the fundamental nature of hate. Extensive experiments show that SHIELD outperforms state-of-the-art methods across datasets and metrics, while demonstrating versatility on other tasks, such as fake news detection.
title Unpacking Hateful Memes: Presupposed Context and False Claims
topic Computation and Language
Artificial Intelligence
68T50, 68T45, 68T07
I.2.7; I.2.10; I.2.6
url https://arxiv.org/abs/2510.09935