Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization

arXiv:2405.02816v1 Announce Type: cross
Abstract: This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior work. Stochastic RAG casts the retrieval process in RAG as a stochastic sampling without replacement process. Through this formulation, we employ straight-through Gumbel-top-k that provides a differentiable approximation for sampling without replacement and enables effective end-to-end optimization for RAG. We conduct extensive experiments on seven diverse …

abstract arxiv assumptions cs.cl cs.ir cs.lg document novel optimization paper prior process rag replacement retrieval retrieval-augmented sampling simplifying stochastic through type utility work