Accelerating materials language processing with large language models

Communications Materials, Год журнала: 2024, Номер 5(1)

Опубликована: Фев. 15, 2024

Abstract Materials language processing (MLP) can facilitate materials science research by automating the extraction of structured data from papers. Despite existence deep learning models for MLP tasks, there are ongoing practical issues associated with complex model architectures, extensive fine-tuning, and substantial human-labelled datasets. Here, we introduce use large models, such as generative pretrained transformer (GPT), to replace architectures prior strategic designs prompt engineering. We find that in-context GPT few or zero-shots provide high performance text classification, named entity recognition extractive question answering limited datasets, demonstrated various classes materials. These also help identify incorrect annotated data. Our GPT-based approach assist material scientists in solving knowledge-intensive even if they lack relevant expertise, offering guidelines applicable any domain. In addition, outcomes expected reduce workload researchers, manual labelling, producing an initial labelling set verifying human-annotations.

Язык: Английский

---

Accelerating the Discovery of Oxygen Reduction Electrocatalysts: High‐Throughput Screening of Element Combinations in Pt‐Based High‐Entropy Alloys

Angewandte Chemie International Edition, Год журнала: 2024, Номер 63(37)

Опубликована: Июнь 27, 2024

The vast number of element combinations and the explosive growth composition space pose significant challenges to development high-entropy alloys (HEAs). Here, we propose a procedural research method aimed at accelerating discovery efficient electrocatalysts for oxygen reduction reaction (ORR) based on Pt-based quinary HEAs. begins with an library provided by large language model (LLM), combined microscale precursor printing pulse high-temperature synthesis techniques prepare multi-element combination HEA array in one step. Through high-throughput measurement using scanning electrochemical cell microscopy (SECCM), precise identification highly active exploration specific are achieved. Advantageous further validated practical electrocatalytic evaluations. contributions individual sites synergistic effects among elements such HEAs enhancing activity elucidated via density functional theory (DFT) calculations. This integrates experiments, catalyst validation, DFT calculations, providing new pathway materials field energy catalysis.

Язык: Английский

---

Large language models for reticular chemistry

Nature Reviews Materials, Год журнала: 2025, Номер unknown

Опубликована: Янв. 31, 2025

Язык: Английский

---

The Road Ahead for Metal–Organic Frameworks: Current Landscape, Challenges and Future Prospects

ACS Nano, Год журнала: 2025, Номер unknown

Опубликована: Янв. 3, 2025

This perspective highlights the transformative potential of Metal-Organic Frameworks (MOFs) in environmental and healthcare sectors. It discusses work that has advanced beyond technology readiness levels >4 including applications capture, storage, conversion gases to value added products. showcases efforts most salient MOFs which have been performed at a great cadence, enabled by federal government, large companies, startups commercialize these technologies despite facing significant challenges. article also forecasts role nanoscale healthcare, strides toward personalized medicine, advocating for their use custom-tailored drug delivery systems. Finally we underscore acceleration MOF research development through integration machine learning AI, positioning as versatile tools poised address global sustainability health

Язык: Английский

---

MOF membranes for gas separations

Progress in Materials Science, Год журнала: 2025, Номер unknown, С. 101432 - 101432

Опубликована: Янв. 1, 2025

---