Researchers from the University of California, Berkeley, have utilized ChatGPT to generate a large-scale dataset for studying metal-organic frameworks used in climate change mitigation. Through prompt engineering, they enabled ChatGPT to extract data from relevant papers with an accuracy rate of 95%. The study indicates that ChatGPT can assist scientists in handling vast amounts of data without the need for programming, thereby accelerating the research process. This could potentially expedite discoveries in related fields and save valuable time. The research also suggests that this method can be applied to other areas of chemistry, demonstrating how AI can accelerate scientific research.
UC Berkeley Team Uses ChatGPT for Research, Completing Years of Student Work in One Hour
站长之家
86
© Copyright AIbase Base 2024, Click to View Source - https://www.aibase.com/news/1155