发表机构
University of Moratuwa; Massey University(莫拉图瓦大学; 梅西大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出Math2Visual-X,一个基于符号生成与LLM路由的模块化框架,用于生成教学对齐的小学低年级数学视觉内容,在覆盖范围和性能上优于现有文本到图像系统。
AI 中文摘要
视觉表示可以帮助小学低年级学习者理解数学应用题,但生成可用于课堂的视觉内容仍然困难。现有的符号系统可控但覆盖范围有限,而端到端的文本到图像系统往往无法满足精确的数学约束。本文提出了一种面向小学低年级数学应用题生成的符号视觉生成框架,具有更广泛的问题覆盖范围和更可扩展的资源生成能力。该框架包括一个基于大语言模型的路由层、三个面向作业单的生成模块,以及两个用于开放世界SVG资源获取的回退机制。一项将Math2Visual-X与Stable Diffusion XL、Nano Banana和GPT Image进行比较的人工评估表明,所提出的方法取得了最强的整体性能。结果表明,该框架为自动数学应用题视觉生成提供了一种可扩展且具有教学依据的方法。
英文摘要
Visual representations can help lower-primary learners understand Math Word Problems, but generating classroom-usable visuals remains difficult. Existing symbolic systems are controllable but limited in coverage, while end-to-end text-to-image systems often fail to satisfy exact mathematical constraints. This paper presents a symbolic visual generation framework for lower-primary MWP generation with broader problem coverage and more scalable asset generation. The framework includes an LLM-based routing layer, three worksheet-oriented generation modules, and two fallback mechanisms for open-world SVG asset acquisition. A human evaluation comparing Math2Visual-X with Stable Diffusion XL, Nano Banana, and GPT Image showed that the proposed method achieved the strongest overall performance. The results indicate that the framework offers a scalable and pedagogically grounded approach for automatic MWP visual generation.
CommentsTo appear in MERCon 2026