Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
This work addresses inefficiencies in plasma simulation parameter selection for researchers, though it is incremental as it builds on existing RAG methods.
The paper tackles the problem of inefficient manual parameter selection in gyrokinetic plasma simulations by introducing Plasma GraphRAG, a framework that integrates Graph Retrieval-Augmented Generation with large language models, resulting in over 10% improvement in overall quality and up to 25% reduction in hallucination rates compared to vanilla RAG.
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.