Materials science in the era of large language models: a perspective
Материаловедение в эпоху больших языковых моделей: перспективный обзор
2024-01-01
SCID: 54.1/pybzanr6
Discuss with AI
knowledge extractionlarge language modelsmaterials scienceprocess automation
Figures from the paper
Abstract (AI)
Large Language Models (LLMs) have garnered considerable interest due to their impressive natural language capabilities, which in conjunction with various emergent properties make them versatile tools in workflows ranging from complex code generation to heuristic finding for combinatorial problems. In this paper we offer a perspective on their applicability to materials science research, arguing their ability to handle ambiguous requirements across a range of tasks and disciplines means they could be a powerful tool to aid researchers. We qualitatively examine basic LLM theory, connecting it to relevant properties and techniques in the literature before providing two case studies that demonstrate their use in task automation and knowledge extraction at-scale. At their current stage of development, we argue LLMs should be viewed less as oracles of novel insight, and more as tireless workers that can accelerate and unify exploration across domains. It is our hope that this paper can familiarise materials science researchers with the concepts needed to leverage these tools in their own research.
Key Findings
1
LLMs can extract and organize materials knowledge at scale from large bodies of information.
2
LLMs can handle ambiguous materials-science tasks that are challenging to formalize with conventional methods.
3
LLMs may automate materials-science processes, improving workflow efficiency and reducing manual effort.
4
Large language models have potential to support materials science across multiple disciplines.
Research Object
the application of Large Language Models (LLMs) in materials science
Research Subject
LLM capabilities for handling ambiguous tasks, automating processes, and extracting knowledge at scale
Publication Details
Publication Date
2024-01-01
Journal
Publisher
ISSN
Cited by
109
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai15
Neural Machine Translation by Jointly Learning to Align and Translate2014
Retrieval-Augmented Generation for Large Language Models: A Survey2023
Emerging Properties in Self-Supervised Vision Transformers2021
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules2018
Training language models to follow instructions with human feedback2022
GPT-4 Technical Report2023
Longformer: The Long-Document Transformer2020
Autonomous chemical research with large language models2023
Multimodal Learning With Transformers: A Survey2023
An autonomous laboratory for the accelerated synthesis of inorganic materials2023
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models2022
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT2023
Explainability for Large Language Models: A Survey2024
Qualitative Spatial Reasoning over Questions (Short Paper)2022