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

Source: [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](<https://www.sota2.com/research/paper/68fa73141e209131cea5a565>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:41:28.462Z

Authors: Hamed Zamani, Michael Bendersky

Published: 2024-05-05T05:42:33.000Z

## 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 datasets on a wide range of tasks, from open-domain question answering to fact verification to slot-filling for relation extraction and to dialogue systems. By applying this optimization method to a recent and effective RAG model, we advance state-of-the-art results on six out of seven datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.02816>)

[PDF](<https://arxiv.org/pdf/2405.02816.pdf>)
