EDUMATH: Generating Standards-aligned Educational Math Word Problems
This addresses the problem of teacher workload in K-12 education by automating MWP customization, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the challenge of generating math word problems (MWPs) customized to student interests and educational standards using LLMs, resulting in a 12B open model matching larger models and a 30B model outperforming closed baselines, with student studies showing similar performance and preference for customized MWPs.
Math word problems (MWPs) are critical K-12 educational tools, and customizing them to students' interests and ability levels can increase learning outcomes. However, teachers struggle to find time to customize MWPs for each student given large class sizes and increasing burnout. We propose that LLMs can support math education by generating MWPs customized to student interests and math education standards. To this end, we use a joint human expert-LLM judge approach to evaluate over 11,000 MWPs generated by open and closed LLMs and develop the first teacher-annotated dataset for standards-aligned educational MWP generation. We show the value of our data by using it to train a 12B open model that matches the performance of larger and more capable open models. We also use our teacher-annotated data to train a text classifier that enables a 30B open LLM to outperform existing closed baselines without any training. Next, we show our models' MWPs are more similar to human-written MWPs than those from existing models. We conclude by conducting the first study of customized LLM-generated MWPs with grade school students, finding they perform similarly on our models' MWPs relative to human-written MWPs but consistently prefer our customized MWPs.