Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separately offers speed but breaks cross-document interaction. We propose Parallel Context-of-Experts Decoding (Pced), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding. Pced treats retrieved documents as isolated "experts", synchronizing their predictions via a novel retrieval-aware contrastive decoding rule that weighs expert logits against the model prior. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents.
@article{arxiv.2601.08670,
title = {Parallel Context-of-Experts Decoding for Retrieval Augmented Generation},
author = {Giulio Corallo and Paolo Papotti},
journal= {arXiv preprint arXiv:2601.08670},
year = {2026}
}