Newest papers

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

Arjun Sundaram, B. Pabitramohan Prusty, Rohit Batra · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29895 · cited by 0 works (OpenAlex) · open-access PDF

Korean

지난 10년 동안, 기계 학습 (ML) 방법을 개발하여 자료 데이터를 추출하고, 가능한 한, 자료 지식을 과학 문학에서 직접 추출했습니다. 이 리뷰는 이 방법의 진화에 기초한 규칙 기반 파이프라인을 통해 천연 언어 처리 (NLP) 모델과 변환기 기반 인코더를 개발했습니다. 마지막으로, 대 언어 모델 (LLM) 및 기관 시스템은 텍스트, 테이블 및 숫자를 포함하여 여러 가지 모드에 걸쳐 자료 정보를 추출 할 수 있습니다. 대규모, 쿼리 가능한 재료 데이터베이스 및 재료 발견을 지원하는 지식 그래프를 구축하는 것 외에도, 우리는 이러한 진보가 어떻게 재료 과학, AI co-scientists 및 chatbots를 통해 재료에 대한 일반적인 질문에 대한 응답과 같은 새로운 기능을 가능하게

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Terminology, Artificial intelligence, Machine learning, Knowledge extraction, Information extraction

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange