EduIllustrate：迈向可扩展的自动多模态教育内容生成
EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content
AI总结：
本文提出EduIllustrate基准，用于评估LLM在K-12 STEM问题中生成图文结合解释的能力，通过230道题和8维度评估标准，揭示LLM在视觉一致性与成本效率上的表现差异。
摘要：
大型语言模型日益被用作教育助手，但其教育能力的评估仍集中于问答和辅导任务。本文提出了EduIllustrate基准，用于评估LLM在K-12 STEM问题中生成图文结合解释的能力。该基准包含230道题，涵盖五个学科和三个年级，采用标准化生成协议，通过顺序锚定确保跨图表视觉一致性，并采用8维度评估标准，基于多媒体学习理论涵盖文本和视觉质量。对十种LLM的评估显示性能差异显著：Gemini 3.0 Pro Preview以87.8%领先，而Kimi-K2.5在成本效率方面最佳（80.8% at $0.12/problem）。工作流程消融分析证实顺序锚定能提高视觉一致性13%，成本降低94%。20名专家评估者验证了LLM作为评判者在客观维度上的可靠性（ρ≥0.83），同时揭示了LLM在主观视觉评估上的局限性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
