ChatMOF is an AI system leveraging large language models (LLMs) like GPT-4, GPT-3.5-turbo, and GPT-3.5-turbo-16k to predict and generate metal-organic frameworks (MOFs). Comprising an agent, toolkit, and evaluator, ChatMOF processes textual inputs, retrieves data, predicts properties, and generates MOF structures. It achieves high accuracy rates (96.9% for searching, 95.7% for predicting, and 87.5% for generating with GPT-4), showcasing the potential of LLMs in materials science.
Publisher
Nature Communications
Published On
Jun 03, 2024
Authors
Yeonghun Kang, Jihan Kim
Tags
AI system
metal-organic frameworks
large language models
property prediction
structure generation
materials science
Related Publications
Explore these studies to deepen your understanding of the subject.
