cs.AI提交于 2026-10-23已译

利用机器学习与大语言模型自动提取材料数据与知识

Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models

Aravindan Kamatchi Sundaram · B. Pabitramohan Prusty · Rohit Batra

中文摘要

过去十年，研究者投入了大量工作，开发机器学习(machine learning, ML)方法，从科学文献中直接提取材料数据，并在可行情况下提取材料知识。综述梳理了相关方法的演进：从启发式、基于规则的流程，到自然语言处理(natural language processing, NLP)模型和基于 Transformer 的编码器，再到能够跨文本、表格和图像等多种模态提取材料信息的大语言模型(large language models, LLMs)及智能体系统。这些进展支持构建大型、可查询的材料数据库和知识图谱，以服务下游材料发现，也带来了材料科学通用问答、AI 科学家、辅助研究的聊天机器人，以及与自主实验室集成后的闭环优化与发现等能力。综述还批判性评估了此类方法生成的数据集、提取准确率和计算成本，比较不同方法的优缺点，并给出构建更可靠、可扩展的材料数据提取流程的实用指南。关键开放问题包括：在样本层面提取完整的材料结构—属性—工艺—性能四面体、缺乏用于系统评估的可靠 benchmark 数据集，以及解决不同文档模态间不统一材料术语的难题。

关键要点

01回顾材料信息提取从规则流程、NPL模型到LLM与智能体系统的演进。
02评估由算法生成的数据集、提取准确率与计算成本，并比较各方法优缺点。
03总结大型材料数据库、知识图谱及材料科学问答等下游能力。
04讨论与自主实验室集成后实现闭环优化与材料发现的路径。
05指出样本级完整信息提取、可靠benchmark及术语统一等开放挑战。

解读

尚无解读。

原始英文摘要

arXiv:2610.29895v1 Announce Type: cross Abstract: Over the past decade, substantial efforts have been devoted to developing machine learning (ML) methods for extracting materials data and, where possible, materials knowledge directly from the scientific literature. This review traces the evolution of these methods from heuristic, rule-based pipelines through natural language processing (NLP) models and transformer-based encoders to, lastly, large language models (LLMs) and agentic systems capable of extracting materials information across multiple modalities, including text, tables, and figures. Beside construction of large, queryable materials databases and knowledge graphs that support downstream materials discovery, we discuss how these advances have enabled new capabilities, such as, generic question answering across materials science, AI co-scientists and chatbots for research assistance, and closed-loop optimization and discovery when integrated with autonomous laboratories. We critically assess the datasets generated using these approaches, their extraction accuracy and computational costs, and the respective strengths and limitations of different methodologies, and even provide practical guidelines for developing more reliable and scalable materials data extraction pipelines. Finally, we identify key open challenges, including the extraction of full materials structure-property-processing-performance tetrahedron at the sample level, the scarcity of reliable benchmark datasets for systematic evaluation, and the resolution of non-standard materials terminology across different document modalities.