用知识图谱+大模型自动推荐等离子体模拟参数，更准更快。
Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
- 构建等离子体领域知识图谱，实现结构化信息检索。
- 相比传统方法，推荐准确率提升10%以上，幻觉率降低25%。
- 适合等离子体物理、核聚变研究者快速启动仿真。
精确的参数选择是开展回旋动力学等离子体模拟的基础，但现有方法严重依赖人工文献调研，效率低且结果不一致。本文提出Plasma GraphRAG框架，将图增强检索生成（GraphRAG）与大语言模型（LLM）结合，实现自动化、物理约束的参数范围识别。通过从精选等离子体文献中构建领域知识图谱，并支持基于图实体与关系的结构化检索，使LLM能生成准确、上下文相关的参数建议。在五个指标（全面性、多样性、可信度、幻觉率、赋能度）上的综合评估表明，Plasma GraphRAG在整体质量上优于普通RAG超过10%，幻觉率最高降低25%。该方法不仅提升了模拟可靠性，也为复杂数据密集型科学领域的发现加速提供了可推广的方法论。
原文摘要 · Abstract (English)
Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a domain-specific knowledge graph from curated plasma literature and enabling structured retrieval over graph-anchored entities and relations, Plasma GraphRAG enables LLMs to generate accurate, context-aware recommendations. Extensive evaluations across five metrics, comprehensiveness, diversity, grounding, hallucination, and empowerment, demonstrate that Plasma GraphRAG outperforms vanilla RAG by over $10\%$ in overall quality and reduces hallucination rates by up to $25\%$. {Beyond enhancing simulation reliability, Plasma GraphRAG offers a methodology for accelerating scientific discovery across complex, data-rich domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。