Prompting for Multimodal Hateful Meme Classification

TL;DR

This paper introduces PromptHate, a prompt-based approach leveraging pre-trained language models for multimodal hateful meme classification, achieving state-of-the-art performance without external knowledge bases.

Contribution

The paper presents a novel prompt-based method that exploits implicit knowledge in PLMs for hateful meme classification, outperforming existing models on benchmark datasets.

Findings

PromptHate achieves an AUC of 90.96.

Prompt-based prompts improve classification accuracy.

Effective use of implicit knowledge in PLMs enhances detection.

Abstract

Hateful meme classification is a challenging multimodal task that requires complex reasoning and contextual background knowledge. Ideally, we could leverage an explicit external knowledge base to supplement contextual and cultural information in hateful memes. However, there is no known explicit external knowledge base that could provide such hate speech contextual information. To address this gap, we propose PromptHate, a simple yet effective prompt-based model that prompts pre-trained language models (PLMs) for hateful meme classification. Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pre-trained RoBERTa language model for hateful meme classification. We conduct extensive experiments on two publicly available hateful and offensive meme datasets. Our experimental results show that PromptHate is able to achieve a high AUC of 90.96, outperforming state-of-the-art baselines on the hateful meme classification task. We also perform fine-grained analyses and case studies on various prompt settings and demonstrate the effectiveness of the prompts on hateful meme classification.