EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content
This addresses the problem of scalable automated educational content generation for K-12 STEM educators and developers, though it is incremental as it focuses on benchmarking rather than a new method.
The paper tackles the lack of evaluation for LLMs in generating multimodal educational content by introducing EduIllustrate, a benchmark for text-diagram explanations in K-12 STEM, and finds that Gemini 3.0 Pro Preview leads with 87.8% performance while sequential anchoring improves visual consistency by 13% at 94% lower cost.
Large language models are increasingly used as educational assistants, yet evaluation of their educational capabilities remains concentrated on question-answering and tutoring tasks. A critical gap exists for multimedia instructional content generation -- the ability to produce coherent, diagram-rich explanations that combine geometrically accurate visuals with step-by-step reasoning. We present EduIllustrate, a benchmark for evaluating LLMs on interleaved text-diagram explanation generation for K-12 STEM problems. The benchmark comprises 230 problems spanning five subjects and three grade levels, a standardized generation protocol with sequential anchoring to enforce cross-diagram visual consistency, and an 8-dimension evaluation rubric grounded in multimedia learning theory covering both text and visual quality. Evaluation of ten LLMs reveals a wide performance spread: Gemini 3.0 Pro Preview leads at 87.8\%, while Kimi-K2.5 achieves the best cost-efficiency (80.8\% at \\$0.12/problem). Workflow ablation confirms sequential anchoring improves Visual Consistency by 13\% at 94\% lower cost. Human evaluation with 20 expert raters validates LLM-as-judge reliability for objective dimensions ($Ï\geq 0.83$) while revealing limitations on subjective visual assessment.