@inproceedings{das-etal-2026-refsafe,
    title = "{REFS}af{E}: A {RAG}-Enabled Framework for Predictive Risk Analysis and Automated Safety Report Generation in Mission-Critical Environments",
    author = "Das, Sanjay  and
      Elgedawy, Ran  and
      Seefried, Ethan  and
      Burchfield, Ryan A.  and
      Wiggins, Gavin  and
      Hewit, Dana  and
      Srinivasan, Sudarshan  and
      Balaprakash, Prasanna  and
      Patton, Robert M.  and
      Thomas, Todd  and
      Ghosal, Tirthankar",
    editor = "Yang, Eugene  and
      Lawrie, Dawn  and
      MacAvaney, Sean  and
      Mayfield, James  and
      Soldaini, Luca  and
      Yates, Andrew",
    booktitle = "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation ({RAG}4{R}eports 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, CA, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.rag4reports-1.6/",
    pages = "47--56",
    ISBN = "979-8-89176-417-0",
    abstract = "Operational safety in mission-critical environments requires AI systems that are accurate, interpretable, and resistant to hallucination. We present an agentic 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 pipeline enables subject matter experts (SMEs) to validate predictions, and provide structured feedback, forming a continuous performance calibration loop. Preliminary deployment demonstrates improved reliability in hazard detection and safety/vulnerability report generation. This work advances trustworthy, evidence-grounded AI for predictive safety intelligence in mission-critical operations."
}