Researchers have developed a specialized AI system that makes vast perovskite solar cell research accessible and actionable for scientists and engineers.

• Created Perovskite-KG, a knowledge graph containing 23,789 entities and 22,272 relationships from 1,517 research papers
• Built domain-specific datasets to enhance LLM performance in perovskite solar cell applications
• Demonstrated superior performance in answering domain-specific queries compared to general-purpose LLMs

This breakthrough addresses the engineering challenge of knowledge fragmentation in rapidly evolving renewable energy research, enabling faster innovation cycles and more efficient knowledge transfer between researchers.

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research