@inproceedings{agarwal-etal-2024-mememqa,
    title = "{M}eme{MQA}: Multimodal Question Answering for Memes via Rationale-Based Inferencing",
    author = "Agarwal, Siddhant  and
      Sharma, Shivam  and
      Nakov, Preslav  and
      Chakraborty, Tanmoy",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-acl.300/",
    doi = "10.18653/v1/2024.findings-acl.300",
    pages = "5042--5078",
    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 - {\textasciitilde}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."
}