Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using General Purpose Language Models

Abstract

Accurate and comprehensive material databases extracted from research papers are crucial for materials science and engineering, but their development requires significant human effort. With large language models (LLMs) transforming the way humans interact with text, LLMs provide an opportunity to revolutionize data extraction. In this study, we demonstrate a simple and efficient method for extracting materials data from full-text research papers leveraging the capabilities of LLMs combined with human supervision. This approach is particularly suitable for mid-sized databases and requires minimal to no coding or prior knowledge about the extracted property. It offers high recall and nearly perfect precision in the resulting database. The method is easily adaptable to new and superior language models, ensuring continued utility. We show this by evaluating and comparing its performance on GPT-3 and GPT-3.5/4 (which underlie ChatGPT), as well as free alternatives such as BART and DeBERTaV3. We provide a detailed analysis of the method's performance in extracting sentences containing bulk modulus data, achieving up to 90% precision at 96% recall, depending on the amount of human effort involved. We further demonstrate the method's broader effectiveness by developing a database of critical cooling rates for metallic glasses over twice the size of previous human curated databases.

13 pages, 4 figures

References in corpus (13)

• Training language models to follow instructions with human feedback
• LLaMA: Open and Efficient Foundation Language Models
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Opportunities and Challenges for Machine Learning in Materials Science
• Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
• Machine-learning rationalization and prediction of solid-state synthesis conditions
• PaperQA: Retrieval-Augmented Generative Agent for Scientific Research
• ChemNLP: A Natural Language Processing based Library for Materials Chemistry Text Data
• Machine Learning Prediction of Critical Cooling Rate for Metallic Glasses From Expanded Datasets and Elemental Features
• Are LLMs Ready for Real-World Materials Discovery?
• Agent-based Learning of Materials Datasets from Scientific Literature
• Inorganic Synthesis Reaction Condition Prediction with Generative Machine Learning

Cited by in corpus (2)

• Visual Analysis of LLM-based Entity Resolution from Scientific Papers
• Machine learning metallic glass critical cooling rates through elemental and molecular simulation based featurization