MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal

TL;DR

This paper introduces MER-Bench, a comprehensive benchmark for evaluating multimodal meme reappraisal, focusing on transforming negative memes into positive ones while maintaining their structure and context, supported by a new evaluation framework.

Contribution

It presents a new task of meme reappraisal, constructs a detailed benchmark dataset with annotations, and proposes a structured evaluation framework for multimodal meme transformation.

Findings

Significant gaps in current models' ability to preserve structure and semantics.

The benchmark enables systematic evaluation of emotion control in meme editing.

Extensive experiments highlight challenges and future directions in multimodal meme reappraisal.

Abstract

Memes represent a tightly coupled, multimodal form of social expression, in which visual context and overlaid text jointly convey nuanced affect and commentary. Inspired by cognitive reappraisal in psychology, we introduce Meme Reappraisal, a novel multimodal generation task that aims to transform negatively framed memes into constructive ones while preserving their underlying scenario, entities, and structural layout. Unlike prior works on meme understanding or generation, Meme Reappraisal requires emotion-controllable, structure-preserving multimodal transformation under multiple semantic and stylistic constraints. To support this task, we construct MER-Bench, a benchmark of real-world memes with fine-grained multimodal annotations, including source and target emotions, positively rewritten meme text, visual editing specifications, and taxonomy labels covering visual type, sentiment polarity, and layout structure. We further propose a structured evaluation framework based on a multimodal large language model (MLLM)-as-a-Judge paradigm, decomposing performance into modality-level generation quality, affect controllability, structural fidelity, and global affective alignment. Extensive experiments across representative image-editing and multimodal-generation systems reveal substantial gaps in satisfying the constraints of structural preservation, semantic consistency, and affective transformation. We believe MER-Bench establishes a foundation for research on controllable meme editing and emotion-aware multimodal generation. Our code is available at: https://github.com/one-seven17/MER-Bench.