Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

TL;DR

This paper introduces Math2Visual, a framework for automatically generating educational visuals for math word problems, creating a new benchmark dataset, and analyzing text-to-image models' effectiveness in producing pedagogically meaningful visuals.

Contribution

The paper presents Math2Visual, a novel framework and dataset for generating educational visuals from math problem texts, and evaluates TTI models' performance in this context.

Findings

Fine-tuned TTI models show improved visual relevance.

Identified key challenges like mathematical relationship misrepresentation.

Established a new benchmark for educational visual generation.

Abstract

Visuals are valuable tools for teaching math word problems (MWPs), helping young learners interpret textual descriptions into mathematical expressions before solving them. However, creating such visuals is labor-intensive and there is a lack of automated methods to support this process. In this paper, we present Math2Visual, an automatic framework for generating pedagogically meaningful visuals from MWP text descriptions. Math2Visual leverages a pre-defined visual language and a design space grounded in interviews with math teachers, to illustrate the core mathematical relationships in MWPs. Using Math2Visual, we construct an annotated dataset of 1,903 visuals and evaluate Text-to-Image (TTI) models for their ability to generate visuals that align with our design. We further fine-tune several TTI models with our dataset, demonstrating improvements in educational visual generation. Our work establishes a new benchmark for automated generation of pedagogically meaningful visuals and offers insights into key challenges in producing multimodal educational content, such as the misrepresentation of mathematical relationships and the omission of essential visual elements.