Beyond the Textual: Generating Coherent Visual Options for MCQs
This work addresses the challenge of scalable, high-quality visual option generation for educational MCQs, which is incremental as it builds on existing textual methods by adding visual components.
The paper tackled the problem of generating multiple-choice questions with visual options, which is often overlooked and costly to create manually, by proposing a Cross-modal Options Synthesis framework that integrates multimodal reasoning and retrieval-augmented generation, resulting in superior performance in content discrimination, question generation, and visual option generation across subjects and educational levels.
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 distractors. 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.