Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for
retrieval models within these systems. Traditional end-to-end evaluation methods are …

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 …

This paper introduces uRAG-a framework with a unified retrieval engine that serves multiple
downstream retrieval-augmented generation (RAG) systems. Each RAG system consumes …

This paper introduces PAG-a novel optimization and decoding approach that guides
autoregressive generation of document identifiers in generative retrieval models through …

Privacy-preserving methods for personalizing large language models (LLMs) are relatively
under-explored. There are two schools of thought on this topic:(1) generating personalized …

Long-text generation is seemingly ubiquitous in real-world applications of large language
models such as generating an email or writing a review. Despite the fundamental …

In the field of language modeling, models augmented with retrieval components have
emerged as a promising solution to address several challenges faced in the natural …

Personalization has emerged as a critical research area in modern intelligent systems,
focusing on mining users' behavioral history and adapting to their preferences for delivering …

Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to
enhance the performance on a wide range of tasks. However, the precise role of user …

Large language models (LLMs) have revolutionized natural language processing with their
exceptional capabilities. However, deploying LLMs on resource-constrained edge devices …