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

2025-02-18

AI Summary

To address the knowledge management and scientific reasoning bottlenecks arising from the rapid proliferation of perovskite solar cell (PSC) literature, this work introduces the first knowledge-enhanced AI system tailored for PSC research. Methodologically, we (1) construct Perovskite-KG—the first domain-specific knowledge graph for PSCs; (2) propose two novel datasets: Perovskite-Chat, a multi-agent-synthesized dialogue dataset, and Perovskite-Reasoning, an expert-annotated scientific reasoning benchmark; and (3) design a dual-model collaborative architecture—comprising separate modules for knowledge-based question answering and scientific reasoning—optimized via domain-adaptive pretraining and instruction fine-tuning. Experimental results demonstrate that our system significantly outperforms general-purpose large language models and existing domain-specific models on both PSC knowledge retrieval and scientific reasoning tasks, delivering efficient, accurate, and interpretable AI-assisted research capabilities.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Develops knowledge-enhanced system for perovskite solar cells.
• Creates datasets and models for materials science research.
• Improves knowledge retrieval and scientific reasoning in PSC research.

Innovation

• Domain-specific knowledge graph
• Multi-agent framework datasets
• Specialized large language models