GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering

Meenu Ravi, Shailik Sarkar, Lulwah AlKulaib +2

Current work on improving reliability in large language model (LLM)- generated answers has primarily leveraged Retrieval-Augmented Generation (RAG), knowledge-graph augmentation, a…