发表机构
TIB Leibniz Information Centre for Science and Technology（莱布尼茨科学技术信息中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SciKGExtract框架，结合大语言模型抽取、化学归一化与智能体细化，从原子层沉积文献中提取工艺知识，显著提升抽取F1分数，验证了化学规范化与智能体验证的互补作用。
AI 中文摘要
材料文献包含详细的实验知识，但由于其以异构形式报告且依赖于特定工艺背景，程序、化学实体和测量结果难以聚合。我们提出了SciKGExtract，一个模式引导的框架，该框架将大语言模型抽取与化学归一化、基于智能体的评估与细化相结合，最终集成到知识图谱中。我们在176篇描述氧化锌（ZnO）和铟镓锌氧化物（IGZO）的原子层沉积论文上评估了该框架，并配有一个专家标注的完整模式子集。PubChem归一化提高了每个测试模型的精确匹配抽取F1分数。对于ZnO，最佳F1分数从直接归一化抽取的0.591提升到智能体细化后的0.805，而IGZO的最佳结果为0.344，揭示了多组分超循环工艺的更大难度。针对包含65个实验属性和155个定量测量节点的深层嵌套模式的评估进一步暴露了工艺分割和数值分配中的错误。这些结果表明，化学规范化与有针对性的智能体验证为将复杂材料文献转化为可重用、机器可操作的实验知识提供了互补的控制手段。
英文摘要
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic verification provide complementary controls for converting complex materials literature into reusable, machine-actionable experimental knowledge.
Comments15 pages, 3 figures, submitted for review to Nature Communications Materials
