AI 考 K12 课本：连前置知识都理不清
现在的 AI 做 K12 考题能拿高分，但一碰到课本里真正的知识结构——比如“学这个之前需要先懂什么”、“这个实验对应哪个概念”——就露馅了。研究者从人教版教材里抽出一个知识图谱，包含9种节点（概念、实验、图片等）和14种关系（前置、包含、视觉对应等），然后出了2.3万道题来考AI。结果最强模型Gemini-3-Flash只答对57%，Gemma-4-31B-IT只有46%，最难的是“前置知识”和“相邻概念”题。他们又用图谱指导微调，只用2300条数据就超过了8个主流训练集的效果。这不是你明天能用上的工具，但它告诉你：AI离真正理解课本还差得远，光刷题没用。
📄 原文摘要(英文)
Large language models are increasingly used in K-12 education, but existing benchmarks mainly test exam question answering rather than understanding how curriculum knowledge is structured and visually presented. We call this capability curriculum cognition. It covers prerequisite chains, concept taxonomies, experiment-concept links, pedagogical sequencing, and visual grounding. We introduce K12-KGraph, a curriculum-aligned knowledge graph extracted from official People's Education Press textbooks in mathematics, physics, chemistry, and biology across primary, middle, and high school. It contains nine node types and fourteen relation types covering curriculum structure and visual grounding. From this graph, we derive K12-Bench, a 23,640-question multi-select benchmark with five task families: Ground, Prereq, Neighbor, Evidence, and Locate. We also build K12-Train, a graph-guided supervised fine-tuning corpus of 7,335 samples, including 2,267 text-only QA pairs and 5,068 multimodal VQA pairs. On K12-Bench, Gemini-3-Flash achieves only 57 percent exact match and Gemma-4-31B-IT reaches 46 percent, with Prereq and Neighbor being the hardest tasks. Our training experiments show that domain-specific supervision can reduce this gap. Under a matched 2,300-sample budget, K12-Train-Text consistently outperforms equally sized subsets of eight mainstream instruction-tuning corpora on GaokaoBench and EduEval. For vision-language models, K12-Train-Full achieves the best overall results on Gaokao-MM, MDK12-medium, and K12Vista among all compared training configurations, despite using fewer samples than the full DataFlow and WizardLM baselines. It also surpasses both text-only and multimodal-only variants, showing that textual and visual supervision are complementary. We release the graph, benchmark, training data, and complete construction pipeline.