AI RESEARCH
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
arXiv CS.CL
•
ArXi:2510.05524v2 Announce Type: replace We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in safety-critical contexts. Using the Operations and Maintenance Intelligence (OMIn) dataset, we construct a QA benchmark spanning global sensemaking and actionable maintenance tasks. KEO builds a structured Knowledge Graph (KG) and integrates it into a retrieval-augmented generation (RAG) pipeline, enabling coherent, dataset-wide reasoning than traditional text-chunk RAG.