Metraipolis › archive › dc_ae006f73b742
Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation — arXiv:2609.22162
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22162
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:05.735Z
- SHA-256 of the archived text
54056ce3199570f6f0f7fc11e9ba28fc983200b8fd5b80da04d21b96ed282efe- Stable URL of this page
https://metraipolis.com/documento/dc_ae006f73b742
How to cite
Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation — arXiv:2609.22162 — arXiv (en), https://arxiv.org/abs/2609.22162 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae006f73b742 (Metraipolis archive dc_ae006f73b742, sha256 54056ce3199570f6f0f7fc11e9ba28fc983200b8fd5b80da04d21b96ed282efe)
BibTeX
@misc{dcae006f73b742,
title = {Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation — arXiv:2609.22162},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22162},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae006f73b742; sha256 54056ce3199570f6f0f7fc11e9ba28fc983200b8fd5b80da04d21b96ed282efe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22162. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation (RAG) improves the factuality of large language models (LLMs) and vision-language models (VLMs) by grounding generation in external knowledge. However, most existing RAG frameworks assume a centralized retrieval corpus, which is often impractical in sensitive domains such as healthcare, where data are inherently distributed and raw content cannot be directly shared across institutions. Recent efforts on decentralized RAG primarily follow prompt-based paradigms that exchange raw, human-readable retrieved content, leading to substantial inference-time computational overhead and direct exposure of retrieved information. To address these limitations, we propose Representation-based Federated RAG (FedRepRAG), a decentralized RAG framework that keeps raw documents at their owning clients and exchanges only compact latent representations during cross-client retrieval. To integrate retrieved knowledge, we introduce a collaboratively trained projector that converts retrieval embeddings into generator-compatible representation tokens for a frozen LLM/VLM backbone. Experiments across decentralized visual question answering (VQA) and question answering (QA) benchmarks show that FedRepRAG consistently outperforms direct inference and local retrieval baselines while substantially reducing retrieval-context length and inference-time computational overhead compared with raw-context transfer. Further analyses confirm the importance of query-relevant retrieved representations and characterize the residual representation-level leakage associated with representation exchange. Overall, FedRepRAG provides an effective and efficient framework for federated RAG without transferring raw retrieved content. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.22162 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:44.855Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).