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 2512.09370cs.DLcond-mat.mtrl-sci
收藏

优化材料科学文献中的数据提取:一种利用大语言模型工具的研究

Optimizing Data Extraction from Materials Science Literature: A Study of Tools Using Large Language Models

Wenkai Ning, Musen Li, Jeffrey R. Reimers, Rika Kobayashi

AI总结:

本研究利用大语言模型评估五种AI工具在材料科学文献中提取带隙数据的效果,探讨其在提升科学发现中的应用与改进方向。

摘要:

大语言模型(LLMs)由于其卓越的自然语言处理(NLP)能力,越来越多地被用于大规模提取和组织无结构数据。赋能材料设计,大量来自实验和模拟的数据散落在众多科学出版物中,但高质量的实验数据库却十分稀缺。本研究考虑了五种代表性AI工具(ChemDataExtractor、BERT-PSIE、ChatExtract、LangChain和Kimi)在从200篇随机选择的材料科学出版物(arXiv和出版版本)中提取带隙方面的有效性与实用性,将结果与人工处理的结果进行比较。尽管数据提取的完整性未达到预期,但在精确度和消除无关论文方面取得了鼓舞人心的结果。我们的分析突显了这些工具的优缺点,为改进未来数据提取技术以促进科学发现和创新提供了见解。结合最近的研究,我们提供了未来数据提取方法可行改进的指导,帮助弥合无结构科学数据与结构化、可操作数据库之间的差距。

英文摘要:

Large Language Models (LLMs) are increasingly utilized for large-scale extraction and organization of unstructured data owing to their exceptional Natural Language Processing (NLP) capabilities. Empowering materials design, vast amounts of data from experiments and simulations are scattered across numerous scientific publications, but high-quality experimental databases are scarce. This study considers the effectiveness and practicality of five representative AI tools (ChemDataExtractor, BERT-PSIE, ChatExtract, LangChain, and Kimi) to extract bandgaps from 200 randomly selected Materials Science publications in two presentations (arXiv and publisher versions), comparing the results to those obtained by human processing. Although the integrity of data extraction has not met expectations, encouraging results have been achieved in terms of precision and the ability to eliminate irrelevant papers from human consideration. Our analysis highlights both the strengths and limitations of these tools, offering insights into improving future data extraction techniques for enhanced scientific discovery and innovation. In conjunction with recent research, we provide guidance on feasible improvements for future data extraction methodologies, helping to bridge the gap between unstructured scientific data and structured, actionable databases.

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。

↑