arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.07584cs.AI
收藏

从论文到属性表:一种基于优先级的LLM工作流用于材料数据提取

From Papers to Property Tables: A Priority-Based LLM Workflow for Materials Data Extraction

Department of Applied Mathematics and Statistics, Johns Hopkins University(约翰霍普金斯大学应用数学与统计系);Department of Mechanical Engineering, Johns Hopkins University(约翰霍普金斯大学机械工程系)

Koushik Rameshbabu, Jing Luo, Ali Shargh, Khalid A. El-Awady, Jaafar A. El-Awady

AI总结:

本文提出一种基于优先级的LLM工作流,用于从科研论文中自动提取和重建结构化材料实验数据,通过整合文本、表格、图表和物理推导信息,以合金劈裂强度为案例,实现了高精度的数据提取与验证。

摘要:

科学数据广泛分散在研究论文中,并且在文本、表格和图表中经常报告不一致,使得手动数据提取和汇总缓慢且容易出错。我们提出了一种基于提示的分层工作流,利用大语言模型(LLM)自动提取和重建结构化的、逐次冲击物理实验记录,通过整合来自全文发表研究论文中分散的信息,使用合金劈裂强度作为代表案例研究。该流程针对每次实验的37个相关实验领域,应用了三级优先级策略:(T1)直接从文本/表格中提取,(T2)使用已验证的控制关系进行物理推导,(T3)在必要时从图表中数字化。提取的值被标准化为规范单位,通过优先级标记以实现可追溯性,并通过物理一致性和合理性检查进行验证。在30篇发表的研究论文基准测试中,包含11,967个评估数据点,该工作流实现了高整体准确率,优先级准确率为94.93%(T1)、92.04%(T2)和83.49%(T3),整体加权准确率为94.69%。跨模型测试进一步表明,对于文本/表格和方程推导字段,结果一致性强,而对于基于图表的提取则一致性和准确性较低。通过API接口实现展示了该方法的可扩展性,实现了一致的提取性能,并在部分测试用例中达到了或超过了基于聊天的准确性。该工作流展示了一种将无结构技术文献转换为可追溯、可分析数据集的实用方法,无需特定任务的微调,从而在材料科学中实现了可扩展的数据库构建。

英文摘要:

Scientific data are widely dispersed across research articles and are often reported inconsistently across text, tables, and figures, making manual data extraction and aggregation slow and error-prone. We present a prompt-driven, hierarchical workflow that uses a large language model (LLM) to automatically extract and reconstruct structured, shot-level shock-physics experimental records by integrating information distributed across text, tables, figures, and physics-based derivations from full-text published research articles, using alloy spall strength as a representative case study. The pipeline targeted 37 experimentally relevant fields per shot and applied a three-level priority strategy: (T1) direct extraction from text/tables, (T2) physics-based derivation using verified governing relations, and (T3) digitization from figures when necessary. Extracted values were normalized to canonical units, tagged by priority for traceability, and validated with physics-based consistency and plausibility checks. Evaluated on a benchmark of 30 published research articles comprising 11,967 evaluated data points, the workflow achieved high overall accuracy, with priority-wise accuracies of 94.93% (T1), 92.04% (T2), and 83.49% (T3), and an overall weighted accuracy of 94.69%. Cross-model testing further indicated strong agreement for text/table and equation-derived fields, with lower agreement for figure-based extraction. Implementation through an API interface demonstrated the scalability of the approach, achieving consistent extraction performance and, in a subset of test cases, matching or exceeding chat-based accuracy. This workflow demonstrates a practical approach for converting unstructured technical literature into traceable, analysis-ready datasets without task-specific fine-tuning, enabling scalable database construction in materials science.

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。

↑