RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915478095527936 |
|---|---|
| author | Walker, Connor Aslansefat, Koorosh Akram, Mohammad Naveed Papadopoulos, Yiannis |
| author_facet | Walker, Connor Aslansefat, Koorosh Akram, Mohammad Naveed Papadopoulos, Yiannis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs Walker, Connor Aslansefat, Koorosh Akram, Mohammad Naveed Papadopoulos, Yiannis Artificial Intelligence Machine Learning 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. |
| title | RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.03768 |