홈 › Papers

Supercharging Federated Intelligence Retrieval

2026-03-26 · Dimitris Stripelis, Patrick Foley, Mohammad Naseri, William Lindskog-Münzing, Chong Shen Ng, Daniel Janes Beutel, Nicholas D. Lane arxiv

RAG typically assumes centralized access to documents, which breaks down when knowledge is distributed across private data silos. We propose a secure Federated RAG system built using Flower that performs local silo retrieval, while server-side aggregation and text generation run inside an attested, confidential compute environment, enabling confidential remote LLM inference even in the presence of honest-but-curious or compromised servers. We also propose a cascading inference approach that incorporates a non-confidential third-party model (e.g., Amazon Nova) as auxiliary context without weakening confidentiality.

📄 PDF Abstract BibTeX arXiv:2603.25374

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems

2025-08-19 · Matey Krastev, Miklos Hamar, Danilo Toapanta, Jesse Brouwers 외 arxiv

This work revisits and extends synthetic query generation pipelines for Neural Information Retrieval (NIR) by leveraging the InPars Toolkit, a reproducible, end-to-end framework for generating training data using large l…

Synthetic Data Generation Information Retrieval

Towards Artificial General or Personalized Intelligence? A Survey on Foundation Models for Personalized Federated Intelligence

2025-05-11 · Yu Qiao, Huy Q. Le, Avi Deb Raha, Phuong-Nam Tran 외

The rise of large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, has reshaped the artificial intelligence landscape. As prominent examples of foundational models (FMs) built on LLMs, these models exhibit …

Computational Efficiency Federated Learning Privacy Preserving RAG+2

Learning Federated Representations and Recommendations with Limited Negatives

2021-08-18 · Lin Ning, Karan Singhal, Ellie X. Zhou, Sushant Prakash

Deep retrieval models are widely used for learning entity representations and recommendations. Federated learning provides a privacy-preserving way to train these models without requiring centralization of user data. How…

Federated Learning Privacy Preserving Retrieval

Federated Retrieval-Augmented Generation: A Systematic Mapping Study

2025-05-24 · Abhijit Chakraborty, Chahana Dahal, Vivek Gupta

Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL), which enables distributed model training without exposing raw data, with Retrieval-Augmented Generation (RAG), which improves the…

Federated Learning Privacy Preserving RAG Retrieval+1

FedCMR: Federated Cross-Modal Retrieval

2021-07-01 · SIGIR 2021 7 · Linlin Zong

Deep cross-modal retrieval methods have shown their competitiveness among different cross-modal retrieval algorithms. Generally, these methods require a large amount of training data. However, aggregating large amounts o…

Cross-Modal Retrieval Federated Learning Retrieval