RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
This addresses safety and accuracy issues in LLM-powered decision support for critical maintenance contexts, representing an incremental improvement over existing RAG methods.
The paper tackled the problem of ensuring both accuracy and safety in Large Language Models for Offshore Wind maintenance by introducing RAGuard, an enhanced Retrieval-Augmented Generation framework that integrates safety-critical documents, resulting in an increase in Safety Recall@K from almost 0% to over 50% while maintaining Technical Recall above 60%.
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.