RAGRoute introduces a neural router for federated RAG that dynamically selects relevant sources, reducing communication by up to 80.65% and latency by 52.50% while preserving accuracy on three benchmarks.
Cache me if you can: The case for retrieval augmentation in federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
RAGRoute introduces a neural router for federated RAG that dynamically selects relevant sources, reducing communication by up to 80.65% and latency by 52.50% while preserving accuracy on three benchmarks.