REFSafE: A RAG-Enabled Framework for Predictive Risk Analysis and Automated Safety Report Generation in Mission-Critical Environments

Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield, Dana Hewit, Sudarshan Srinivasan, Prasanna Balaprakash, Robert M. Patton, Todd Thomas, Tirthankar Ghosal

Keywords: Retrieval Augmented Generation, Reports, Operational Safety, Smart Retrieval, Mission-critical Environments

Abstract:

Operational safety in mission-critical environments requires AI systems that are accurate, interpretable, and resistant to hallucination. We present a Retrieval-Augmented Generation (RAG) framework, REFSafe, for grounded hazard analysis and automated safety report generation. The system integrates Large Language Models (LLMs) with structured operational data, historical incident repositories, policy documents, and external authoritative sources. Through iterative agentic reasoning, the framework retrieves, verifies, and synthesizes evidence prior to generation, enforcing citation-backed outputs with explicit source attribution (documents, links, and prior events) to ensure traceability and trust.

To mitigate hallucinations and unsupported claims, all risk assessments and forecasts are constrained to retrieved evidence, with confidence signals derived from retrieval relevance and source consistency. A transparent human-in-the-loop pipeline enables subject matter experts (SMEs) to validate predictions, refine retrieved context, and provide structured feedback, forming a continuous performance calibration loop. Preliminary deployment demonstrates improved reliability in hazard detection and reduced report generation latency. This work advances trustworthy, evidence-grounded AI for predictive safety intelligence in mission-critical operations.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 9