Metraipolis › archive › dc_3df420938656
Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction — arXiv:2609.33037
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33037
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:39:54.045Z
- SHA-256 of the archived text
eb2673a2567a5596f07f8ae356410e0dcfa9e61b4cde3bf885250b672b91f108- Stable URL of this page
https://metraipolis.com/documento/dc_3df420938656
How to cite
Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction — arXiv:2609.33037 — arXiv (en), https://arxiv.org/abs/2609.33037 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3df420938656 (Metraipolis archive dc_3df420938656, sha256 eb2673a2567a5596f07f8ae356410e0dcfa9e61b4cde3bf885250b672b91f108)
BibTeX
@misc{dc3df420938656,
title = {Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction — arXiv:2609.33037},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33037},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3df420938656; sha256 eb2673a2567a5596f07f8ae356410e0dcfa9e61b4cde3bf885250b672b91f108},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33037. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections, such as medical records, cannot be pooled because of privacy rules. Federated RAG leaves each collection with its owner, or node, which scores candidate answers from its own documents; a central hub combines the scores. Some nodes, called Byzantine, may be compromised, faulty, or misled by instructions hidden in documents, and report arbitrary scores. Conformal prediction returns a set containing the correct answer with a chosen probability, using a cutoff set in a calibration step on questions with known answers. An unknown group of nodes, no larger than a declared bound, may misreport both in this step and at query time. Existing methods assume every node is honest or protect only the calibration step. We observe that the honest nodes are the same in both steps. The hub therefore has all nodes score the same calibration questions, and keeps a candidate only if some plausible group of honest nodes, using its own scores in both steps, would keep it. We prove that the resulting sets contain the correct answer with the chosen probability in finite samples, whatever the Byzantine nodes report. No method using the same information can return smaller sets without risking the loss of an answer the honest nodes support. If nodes fail at random, the guarantee weakens only by the probability that more nodes fail than declared. In simulations, on real question-answering tasks including medical exams, and with language models as nodes, some hijacked, our sets reached the target whenever no more nodes misbehaved than declared, while plain averaging could miss it. They were also clearly smaller than those of simpler methods with the same protection, most of all when the declared bound was generous, so a cautious bound costs little. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33037 — 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 2026-10-07T22:14:28.681Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).