Congratulations to undergraduate students Shrey Modi, Anna Latosinska, Jinming Zhang, Ching-Wen Wang, Shanonan Wang, and Ayan Deep Hazra for their contributions and co-authorship on their work titled “Flexible, model-agnostic method for materials data extraction from text using general purpose language models”! The team submitted their paper for review at the beginning of the year and it has now been accepted for publication!
As the team explored various workflows for using LLMs they analyzed a series of methods to understand their performance in extracting sentences containing bulk modulus data, achieving up to 90% precision at 96% recall, depending on the amount of human effort involved. They further demonstrated the method’s broader effectiveness by developing a database of critical cooling rates for metallic glasses over twice the size of previous human curated databases.
Check out the publication in Digital Discovery or via arXiv!