@inproceedings{corallo-papotti-2026-parallel,
    title = "Parallel Context-of-Experts Decoding for Retrieval Augmented Generation",
    author = "Corallo, Giulio  and
      Papotti, Paolo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1635/",
    pages = "32666--32676",
    ISBN = "979-8-89176-395-1",
    abstract = "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 retrieval-aware extension of context-aware decoding. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents."
}