Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization
This work addresses the challenge of improving retrieval-augmented generation for tasks like question answering and dialogue systems, representing an incremental advancement over prior methods.
The paper tackles the problem of optimizing retrieval-augmented generation models by relaxing assumptions of marginalization and document independence, introducing Stochastic RAG as a novel end-to-end approach. It achieves state-of-the-art results on six out of seven diverse datasets, including open-domain question answering and fact verification.
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.