对比三种检索生成方法，提升无线网络编程的准确性与可靠性。
Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)
- 用向量、图谱和混合检索增强大模型生成能力
- 混合图谱检索使事实正确率提升8%，图谱检索提升11%上下文相关性
- 为电信领域AI生成提供可量化评估的新范式，适合网络自动化研发者
生成式人工智能有望在未来的无线网络中实现自主优化。在ORAN架构下，大语言模型可通过RAN智能控制器平台的规范和API定义，生成xApps和rApps。然而，针对通信任务对基础大模型进行微调成本高、资源消耗大。检索增强生成（RAG）通过上下文学习提供了一种无需全量重训的实用替代方案。传统RAG依赖向量检索，而新兴的GraphRAG与Hybrid GraphRAG引入知识图谱或双路检索策略，支持多跳推理并提升事实依据。尽管前景广阔，这些方法在关键领域如ORAN中仍缺乏系统性、指标驱动的评估。本研究基于ORAN规范，对比了向量RAG、GraphRAG与Hybrid GraphRAG性能，采用忠实性、答案相关性、上下文相关性和事实正确性等生成指标，评估不同问题复杂度下的表现。结果表明，GraphRAG与Hybrid GraphRAG均优于传统RAG；其中，Hybrid GraphRAG将事实正确率提升8%，GraphRAG使上下文相关性提高11%。
原文摘要 · Abstract (English)
Generative AI (GenAI) is expected to play a pivotal role in enabling autonomous optimization in future wireless networks. Within the ORAN architecture, Large Language Models (LLMs) can be specialized to generate xApps and rApps by leveraging specifications and API definitions from the RAN Intelligent Controller (RIC) platform. However, fine-tuning base LLMs for telecom-specific tasks remains expensive and resource-intensive. Retrieval-Augmented Generation (RAG) offers a practical alternative through in-context learning, enabling domain adaptation without full retraining. While traditional RAG systems rely on vector-based retrieval, emerging variants such as GraphRAG and Hybrid GraphRAG incorporate knowledge graphs or dual retrieval strategies to support multi-hop reasoning and improve factual grounding. Despite their promise, these methods lack systematic, metric-driven evaluations, particularly in high-stakes domains such as ORAN. In this study, we conduct a comparative evaluation of Vector RAG, GraphRAG, and Hybrid GraphRAG using ORAN specifications. We assess performance across varying question complexities using established generation metrics: faithfulness, answer relevance, context relevance, and factual correctness. Results show that both GraphRAG and Hybrid GraphRAG outperform traditional RAG. Hybrid GraphRAG improves factual correctness by 8%, while GraphRAG improves context relevance by 11%.
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。