LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation

ArXi:2605.07517v1 Announce Type: cross Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat naturally structured corpora, such as technical manuals, as flat collections of passages, thereby overlooking the hyperlink topology that users rely on when navigating such content.