Date
Publisher
arXiv
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.
Study at a glance
- Question: How well can AI generate helpful visual illustrations for math word problems?
- Setting and data: Interviews with math teachers and an annotated dataset of 1,903 visuals
- Method: Teacher interviews, framework development, and testing and training of text-to-image AI models
Why it matters
Visuals help young learners interpret math word problems 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.
Key findings
- For young learners' math word problems, training image-generating AI on 1,903 teacher-informed visual examples improved its ability to create educational illustrations.
- Current text-to-image tools frequently misrepresent the core mathematical relationships described in word problem text.
- These AI tools often omit essential visual elements needed to help students interpret word problems into mathematical expressions.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
