Perovskite LLM

Home About Perovskite LLM Contact us Chinese

Perovskite LLM ——HKUST(GZ)

What can we do

Automated Knowledge Graph Construction Feature

Our automated knowledge graph construction feature efficiently extracts entities and relationships from a vast number of scientific publications, organizing them into a unified knowledge graph. The process includes document collection, entity extraction, relationship extraction, and the final integration and visualization of the knowledge graph. Learn more

Perovskite Large Language Model

Our novel perovskite LLM is specifically trained on extensive materials science literature to excel at domain-specific question answering and knowledge extraction. Through advanced data processing and intelligent validation mechanisms, this model enhances the precision and depth of responses in the context of perovskite materials. Learn more

AI Lab

We are in the process of establishing an AI Lab focused on the automation of material preparation processes. This cutting-edge lab will utilize AI-powered robotic arms to carry out essential tasks such as titration, solution addition, and other complex procedures involved in material synthesis. Learn more

Demo

Latest Update

Our paper “Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research” has been accepted to Findings of Nature Language Processing Conference EMNLP 2025! If you are interested in our work, please consider citing it:

@inproceedings{liu-etal-2025-perovskite,
    title = "Perovskite-{LLM}: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research",
    author = "Liu, Xiang  and
      Sun, Penglei  and
      Chen, Shuyan  and
      Zhang, Longhan  and
      Dong, Peijie  and
      You, Huajie  and
      Zhang, Yongqi  and
      Yan, Chang  and
      Chu, Xiaowen  and
      Zhang, Tong-yi",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.27/",
    doi = "10.18653/v1/2025.findings-emnlp.27",
    pages = "494--518",
    ISBN = "979-8-89176-335-7"
}

Innovative Insights. Accelerated Research. Future Exploration.

Try Perovskite LLM