MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing

TL;DR

MemeMQA introduces a multimodal question-answering framework for memes that combines reasoning and explanations, supported by a new dataset and outperforming baselines in accuracy and semantic alignment.

Contribution

This paper presents MemeMQA, a novel multimodal framework with a new dataset and reasoning capabilities, advancing meme understanding and interpretability.

Findings

MemeMQA achieves ~18% higher answer accuracy than baselines.

It provides coherent explanations alongside answers.

The framework demonstrates robustness across diverse question sets.

Abstract

Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects. Previous studies have analyzed memes in closed settings - detecting harm, applying semantic labels, and offering natural language explanations. To extend this research, we introduce MemeMQA, a multimodal question-answering framework aiming to solicit accurate responses to structured questions while providing coherent explanations. We curate MemeMQACorpus, a new dataset featuring 1,880 questions related to 1,122 memes with corresponding answer-explanation pairs. We further propose ARSENAL, a novel two-stage multimodal framework that leverages the reasoning capabilities of LLMs to address MemeMQA. We benchmark MemeMQA using competitive baselines and demonstrate its superiority - ~18% enhanced answer prediction accuracy and distinct text generation lead across various metrics measuring lexical and semantic alignment over the best baseline. We analyze ARSENAL's robustness through diversification of question-set, confounder-based evaluation regarding MemeMQA's generalizability, and modality-specific assessment, enhancing our understanding of meme interpretation in the multimodal communication landscape.