为大型语言模型维护安全，设计了双索引检索增强框架
RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
- 分两路检索技术与安全文档，分别分配检索预算
- 安全召回率从0%提升至50%以上，技术召回率超60%
- 适合高风险工业场景的智能决策支持系统
海上风电运维对准确性和安全性要求极高，传统大语言模型在面对高度专业化或意外场景时表现不佳。我们提出RAGuard，一种增强型检索增强生成框架，显式融合安全关键文档与技术手册。通过向两个索引并行查询，并为知识和安全分别分配独立检索预算，RAGuard确保技术深度与安全覆盖双重保障。进一步开发SafetyClamp扩展，扩大候选池并“硬夹紧”精确安全项的保证。我们在稀疏（BM25）、稠密（密集段落检索）和混合检索范式下进行评估，测量技术召回率@K和安全召回率@K。RAGuard的两项改进使安全召回率@K从原始RAG的近0%提升至超过50%，同时保持技术召回率高于60%。结果表明，RAGuard与SafetyClamp有望为关键运维场景中集成安全保障的LLM决策支持建立新标准。
原文摘要 · Abstract (English)
Accuracy and safety are paramount in Offshore Wind (OSW) maintenance, yet conventional Large Language Models (LLMs) often fail when confronted with highly specialised or unexpected scenarios. We introduce RAGuard, an enhanced Retrieval-Augmented Generation (RAG) framework that explicitly integrates safety-critical documents alongside technical manuals.By issuing parallel queries to two indices and allocating separate retrieval budgets for knowledge and safety, RAGuard guarantees both technical depth and safety coverage. We further develop a SafetyClamp extension that fetches a larger candidate pool, "hard-clamping" exact slot guarantees to safety. We evaluate across sparse (BM25), dense (Dense Passage Retrieval) and hybrid retrieval paradigms, measuring Technical Recall@K and Safety Recall@K. Both proposed extensions of RAG show an increase in Safety Recall@K from almost 0\% in RAG to more than 50\% in RAGuard, while maintaining Technical Recall above 60\%. These results demonstrate that RAGuard and SafetyClamp have the potential to establish a new standard for integrating safety assurance into LLM-powered decision support in critical maintenance contexts.
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。