[论文解读] Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design

Arjun Sundaram, Mohit Chakraborty+3 more|arXiv (Cornell University)|Feb 4, 2026

Machine Learning in Materials Science被引用 0

一句话总结

该论文开发了一个基于大语言模型的两阶段管线，从文本和表格中提取合金数据，覆盖HEA文献，构建用于可持续材料设计的大型数据库，并在三个领域展示应用。

ABSTRACT

The design of sustainable materials requires access to materials performance and sustainability data from literature corpus in an organized, structured and automated manner. Natural language processing approaches, particularly large language models (LLMs), have been explored for materials data extraction from the literature, yet often suffer from limited accuracy or narrow scope. In this work, an LLM-based pipeline is developed to accurately extract alloy-related information from both textual descriptions and tabular data across the literature on high-entropy (or multicomponent) alloys (HEA). Specifically two databases with 37,711 and 148,069 entries respectively are retrieved; one from the literature text, consisting of alloy composition, processing conditions, characterization methods, and reported properties, and other from the literature tables, consisting of property names, values, and units. The pipeline enhances materials-domain sensitivity through prompt engineering and retrieval-augmented generation and achieves F1-scores of 0.83 for textual extraction and 0.88 for tabular extraction, surpassing or matching existing approaches. Application of the pipeline to over 10,000 articles yields the largest publicly available multicomponent alloy database and reveals compositional and processing-property trends. The database is further employed for sustainability-aware materials selection in three application domains, i.e., lightweighting, soft magnetic, and corrosion-resistant, identifying multicomponent alloy candidates with more sustainable production while maintaining or exceeding benchmark performance. The pipeline developed can be easily generalized to other class of materials, and assist in development of comprehensive, accurate and usable databases for sustainable materials design.

研究动机与目标

• 将未结构化文献转换为可机器读取的结构化数据，以支持可持续材料设计的需要。
• 开发一个鲁棒、可泛化的数据提取管线，使用LLMs处理文本和表格数据，适用于多样的合金报道风格。
• 从文本和表格创建两大数据库，为后续的可持续性感知材料选择提供支持。
• 公开发布经筛选的数据库，以支持HEAs及其他领域的更广泛研究。

提出的方法

• 两阶段提取管线：(i) 段落级文本提取，捕获合金体系、加工、表征和性能；(ii) 基于表格的提取，捕获性能值、单位和条件。
• Query Set 1（QS1）使用提示工程、少量示例和检索增强生成（RAG）来从摘要和实验章节识别合金成分、加工和性能。
• Query Set 2（QS2）将表格单元映射到一个 curated 的主属性词汇表（共354项），通过两遍的LLM方法先识别标准化属性名，再提取相应的数值和条件。
• 从数据库DB1构建主属性词汇表，进行归一化并扩展符号/名称集合，以实现对表格的鲁棒映射。
• 使用扩展的混淆矩阵框架进行评估，以考虑缺失、幻觉和新条目，突出精确度/召回率/F1值的权衡。
• 管线选择GPT-4o与GPT-4o mini以在成本与精度之间取得平衡，并结合向量数据库中的98个专家注释示例进行少量示例演示的RAG。

Figure 1: Overall LLM-based alloy data extraction pipeline developed in this work. Starting from list of article DOIs, different sections of the article were separately extracted in XML format using publisher APIs. This data was selectively passed through two LLM extractor consisting of two query se

实验结果

研究问题

• RQ1 一个基于LLM的管线是否能够在大规模HEA文献语料中，准确从文本和表格提取合金成分、加工细节和属性？
• RQ2 与专家基准相比，文本（QS1）和表格（QS2）的可达成的精确度、召回率和F1是多少？
• RQ3 得到的数据库有多大、可用性如何，能否在多个领域提供面向可持续性的材料选择？
• RQ4 基于LLM的多组分合金提取在实际应用中面临哪些挑战与限制，如何缓解？

主要发现

• 建立了两大数据库：文本派生的合金记录DB1为37,711条，表格派生的记录DB2为148,069条，来自10,829篇文章。
• QS1在专家注释的评审数据上实现了约0.83的F1分数。
• QS2在广泛测试集上实现约0.88的F1，在聚焦力学性能的集合上实现约0.96的F1。
• 文本提取在评审数据上的精确度/召回率对QS1分别为0.81与0.86；表格提取的精确度/召回率分别为0.98与0.81。
• 建立的数据库使在轻量化结构材料、软磁性及耐腐蚀领域的可持续性导向选择成为可能，能够识别在不降低性能的前提下具有更好可持续性的多组分合金。
• Alloy Tattvasar 平台向公众开放，供社区重复使用和访问经过筛选的数据库。

Figure 2: a) Schematic of the QS1 prompt structure, comprising system and formatting instructions, domain-specific context, RAG-selected few-shot examples, and user query with the target article paragraph, organized in a chain-of-thought framework. b) QS1 data extraction workflow for a single articl