← all papers · overview

Question-based Retrieval Using Atomic Units For Enterprise RAG

Abstract

Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).