SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
Indexing is an important step towards strong performance in retrieval-augmented generation (RAG) systems. However, existing methods organize data based on either semantic similarity (similarity) or related information (relatedness), but do not cover both perspectives comprehensively. Our analysis reveals that modeling only one perspective results in insufficient knowledge synthesis, leading to …