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

2024-07-30

arXiv.org

AI Summary

To address the failure of conventional two-stream methods in detecting hate memes due to their continuous evolutionary dynamics, this paper proposes Chain-of-Evolution (CoE), a novel prompting framework leveraging Large Multimodal Models (LMMs). CoE is the first to explicitly incorporate meme evolution relationships into LMM-based reasoning through a two-stage “retrieve–extract–amplify” architecture. It jointly identifies evolutionary meme pairs, extracts underlying semantic patterns, and amplifies contextual hate signals—yielding interpretable and adaptive detection. The framework is compatible with mainstream LMMs (e.g., LLaVA, Qwen-VL) and achieves significant improvements over state-of-the-art methods on FHM, MAMI, and HarM benchmarks. Moreover, CoE generates visualizable evolution paths, enabling systematic analysis of meme evolution mechanisms and supporting deeper understanding of how hate content propagates and adapts across multimodal contexts.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models
• Natural Language Processing: (Large) Language Models

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Detecting evolving hateful memes with cultural changes
• Improving Large Multimodal Models for meme hatefulness detection
• Simulating meme evolution process through Chain-of-Evolution prompting

Innovation

• Chain-of-Evolution Prompting for meme analysis
• Evolutionary pair mining with external meme sets
• Contextual relevance amplification for hatefulness detection