Large language models predict MOF synthesis scale-up with 93.5% accuracy

Researchers have developed ScaleMOF, a new dataset and learning strategy designed to predict the scalability of metal-organic framework (MOF) syntheses. By fine-tuning large language models, this approach aims to bridge the gap between MOF discovery and industrial application by identifying promising candidates for scale-up. The proof-of-concept system achieved 93.5% accuracy, serving as a literature-grounded tool for prioritizing MOF scale-up. AI

IMPACT This research demonstrates a novel application of LLMs in materials science, potentially accelerating the industrial adoption of newly discovered MOFs.

RANK_REASON The cluster describes a research paper detailing a new method for predicting material synthesis scale-up using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Hugging Face
• large language models
• metal-organic framework
• ScaleMOF
• Zhiling Zheng

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →