AtomRAG: atomic query decomposition for multi-hop retrieval-augmented generation Nikita Igolnikov* [1] , Noorhan Abbas [1] ++...

https://www.academia.edu/3071-0286/2/2/10.20935/AcadAI8242 Introduction: Standard Retrieval-Augmented Generation (RAG) often fails on multi-hop queries that require the synthesis of information from multiple sources. To address this limitation, we propose AtomRAG, a chain-of-prompts algorithm that decomposes a complex query into a series of atomic requirements for information retrieval. https://www.academia.edu/journals/academia-ai-and-applications/articles?source=journal-top-nav