Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jinfa, Pan, Jinsheng, Wan, Zhongwei, Lyu, Hanjia, Luo, Jiebo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916573454794752
author Huang, Jinfa
Pan, Jinsheng
Wan, Zhongwei
Lyu, Hanjia
Luo, Jiebo
author_facet Huang, Jinfa
Pan, Jinsheng
Wan, Zhongwei
Lyu, Hanjia
Luo, Jiebo
contents Recent advances show that two-stream approaches have achieved outstanding performance in hateful meme detection. However, hateful memes constantly evolve as new memes emerge by fusing progressive cultural ideas, making existing methods obsolete or ineffective. In this work, we explore the potential of Large Multimodal Models (LMMs) for hateful meme detection. To this end, we propose Evolver, which incorporates LMMs via Chain-of-Evolution (CoE) Prompting, by integrating the evolution attribute and in-context information of memes. Specifically, Evolver simulates the evolving and expressing process of memes and reasons through LMMs in a step-by-step manner. First, an evolutionary pair mining module retrieves the top-k most similar memes in the external curated meme set with the input meme. Second, an evolutionary information extractor is designed to summarize the semantic regularities between the paired memes for prompting. Finally, a contextual relevance amplifier enhances the in-context hatefulness information to boost the search for evolutionary processes. Extensive experiments on public FHM, MAMI, and HarM datasets show that CoE prompting can be incorporated into existing LMMs to improve their performance. More encouragingly, it can serve as an interpretive tool to promote the understanding of the evolution of social memes. [Homepage] (https://github.com/inFaaa/Evolver)
format Preprint
id arxiv_https___arxiv_org_abs_2407_21004
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection
Huang, Jinfa
Pan, Jinsheng
Wan, Zhongwei
Lyu, Hanjia
Luo, Jiebo
Computation and Language
Computer Vision and Pattern Recognition
Recent advances show that two-stream approaches have achieved outstanding performance in hateful meme detection. However, hateful memes constantly evolve as new memes emerge by fusing progressive cultural ideas, making existing methods obsolete or ineffective. In this work, we explore the potential of Large Multimodal Models (LMMs) for hateful meme detection. To this end, we propose Evolver, which incorporates LMMs via Chain-of-Evolution (CoE) Prompting, by integrating the evolution attribute and in-context information of memes. Specifically, Evolver simulates the evolving and expressing process of memes and reasons through LMMs in a step-by-step manner. First, an evolutionary pair mining module retrieves the top-k most similar memes in the external curated meme set with the input meme. Second, an evolutionary information extractor is designed to summarize the semantic regularities between the paired memes for prompting. Finally, a contextual relevance amplifier enhances the in-context hatefulness information to boost the search for evolutionary processes. Extensive experiments on public FHM, MAMI, and HarM datasets show that CoE prompting can be incorporated into existing LMMs to improve their performance. More encouragingly, it can serve as an interpretive tool to promote the understanding of the evolution of social memes. [Homepage] (https://github.com/inFaaa/Evolver)
title Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.21004