钙钛矿-大语言模型：面向钙钛矿太阳能电池研究的知识增强型大语言模型

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

February 18, 2025

作者: Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang

cs.AI

摘要

钙钛矿太阳能电池（PSCs）的快速发展引发了研究文献的指数级增长，这迫切要求在该领域建立高效的知识管理与推理系统。我们提出了一套全面的知识增强系统，专为PSCs设计，整合了三大核心组件。首先，我们构建了Perovskite-KG，这是一个基于1,517篇研究论文构建的领域知识图谱，包含23,789个实体和22,272条关系。其次，我们创建了两个互补的数据集：Perovskite-Chat，包含通过新型多智能体框架生成的55,101对高质量问答对；以及Perovskite-Reasoning，收录了2,217个精心筛选的材料科学问题。第三，我们引入了两个专门的大型语言模型：Perovskite-Chat-LLM，用于提供领域知识辅助；Perovskite-Reasoning-LLM，专注于科学推理任务。实验结果表明，我们的系统在领域知识检索与科学推理任务上均显著超越现有模型，为PSC研究中的文献综述、实验设计及复杂问题解决提供了强有力的工具支持。

English

The rapid advancement of perovskite solar cells (PSCs) has led to an exponential growth in research publications, creating an urgent need for efficient knowledge management and reasoning systems in this domain. We present a comprehensive knowledge-enhanced system for PSCs that integrates three key components. First, we develop Perovskite-KG, a domain-specific knowledge graph constructed from 1,517 research papers, containing 23,789 entities and 22,272 relationships. Second, we create two complementary datasets: Perovskite-Chat, comprising 55,101 high-quality question-answer pairs generated through a novel multi-agent framework, and Perovskite-Reasoning, containing 2,217 carefully curated materials science problems. Third, we introduce two specialized large language models: Perovskite-Chat-LLM for domain-specific knowledge assistance and Perovskite-Reasoning-LLM for scientific reasoning tasks. Experimental results demonstrate that our system significantly outperforms existing models in both domain-specific knowledge retrieval and scientific reasoning tasks, providing researchers with effective tools for literature review, experimental design, and complex problem-solving in PSC research.