Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
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.
Related
- Agentic schema-guided extraction of materials process knowledge from scientific literature
- Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials
- Automated Symbolic Derivation Enables Scalable Ensemble DFT for Strongly Correlated Molecules and Materials
- From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
- An Automated and Reproducible Workflow for Crack Identification and Damage Assessment of Fusion Materials
BibTeX
@misc{sundaram2026automated,
title = {{Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models}},
author = {Aravindan Kamatchi Sundaram and B. Pabitramohan Prusty and Rohit Batra},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29895},
eprint = {2610.29895},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29895},
}
RIS
TY - UNPB
TI - Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
AU - Aravindan Kamatchi Sundaram
AU - B. Pabitramohan Prusty
AU - Rohit Batra
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29895
UR - https://arxiv.org/abs/2610.29895
AB - 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.
ER -