@inproceedings{wang-etal-2025-beyond-textual,
    title = "Beyond the Textual: Generating Coherent Visual Options for {MCQ}s",
    author = "Wang, Wanqiang  and
      He, Longzhu  and
      Zheng, Wei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.365/",
    doi = "10.18653/v1/2025.findings-emnlp.365",
    pages = "6918--6935",
    ISBN = "979-8-89176-335-7",
    abstract = "Multiple-choice questions (MCQs) play a crucial role in fostering deep thinking and knowledge integration in education. However, previous research has primarily focused on generating MCQs with textual options, but it largely overlooks the visual options. Moreover, generating high-quality distractors remains a major challenge due to the high cost and limited scalability of manual authoring. To tackle these problems, we propose a Cross-modal Options Synthesis (CmOS), a novel framework for generating educational MCQs with visual options. Our framework integrates Multimodal Chain-of-Thought (MCoT) reasoning process and Retrieval-Augmented Generation (RAG) to produce semantically plausible and visually similar answer and distractor. It also includes a discrimination module to identify content suitable for visual options. Experimental results on test tasks demonstrate the superiority of CmOS in content discrimination, question generation and visual option generation over existing methods across various subjects and educational levels."
}