EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914464533577728 |
|---|---|
| author | Bi, Shuzhen Zhang, Mingzi Li, Zhuoxuan Wang, Xiaolong Li, Keqian Zhou, Aimin |
| author_facet | Bi, Shuzhen Zhang, Mingzi Li, Zhuoxuan Wang, Xiaolong Li, Keqian Zhou, Aimin |
| contents | 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 ($ρ\geq 0.83$) while revealing limitations on subjective visual assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05005 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content Bi, Shuzhen Zhang, Mingzi Li, Zhuoxuan Wang, Xiaolong Li, Keqian Zhou, Aimin Computers and Society Artificial Intelligence Computation and Language 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 ($ρ\geq 0.83$) while revealing limitations on subjective visual assessment. |
| title | EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content |
| topic | Computers and Society Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.05005 |