Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations

TL;DR

Plasma GraphRAG is a novel framework combining graph retrieval and large language models to automate and improve physics-grounded parameter selection in gyrokinetic plasma simulations.

Contribution

It introduces a domain-specific knowledge graph integrated with LLMs to automate parameter recommendations, reducing manual effort and increasing accuracy.

Findings

Outperforms vanilla RAG by over 10% in overall quality.

Reduces hallucination rates by up to 25%.

Demonstrates effectiveness across five evaluation metrics.

Abstract

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.