Metraipolis › archive › dc_62079170f968

ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens — arXiv:2611.00871

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00871
License (as archived)
CC0-1.0
Archived
2026-11-03T18:16:20.814Z
SHA-256 of the archived text
70d15b9e05ce486d8f8a4ffd9ed404e3f8d33ce0430ab8451a4b0102e574ffea
Stable URL of this page
https://metraipolis.com/documento/dc_62079170f968

How to cite

ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens — arXiv:2611.00871 — arXiv (en), https://arxiv.org/abs/2611.00871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62079170f968 (Metraipolis archive dc_62079170f968, sha256 70d15b9e05ce486d8f8a4ffd9ed404e3f8d33ce0430ab8451a4b0102e574ffea)
BibTeX
@misc{dc62079170f968,
  title = {ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens — arXiv:2611.00871},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00871},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62079170f968; sha256 70d15b9e05ce486d8f8a4ffd9ed404e3f8d33ce0430ab8451a4b0102e574ffea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite advances in retrieval-augmented generation (RAG), suppressing hallucinations during complex reasoning remains a persistent challenge. We identify that existing RAG pipelines suffer from a textual bottleneck: by passing only raw text to the generator, they discard discriminative signals of the retriever. Furthermore, recent attempts to unify retrieval and generation within a single LLM induce severe objective conflict and exacerbate the rank collapse of decoder-only architectures, degrading performance on both tasks. To address these limitations, we introduce ShiftRAG, a decoupled RAG framework that employs a single LLM backbone but isolates discriminative retrieval learning from autoregressive generation. To bridge these decoupled modes, we project retrieval alignments into continuous soft tokens, establishing a high-bandwidth interface that infuses the generator with retrieval-side signals. Concurrently, our soft orthogonality objective mitigates rank collapse, while layer-wise relevance dynamics preserve the fine-grained latent space required for highly discriminative evidence separation. Extensive evaluations demonstrate that ShiftRAG significantly improves retrieval and question answering performance over state-of-the-art baselines. ShiftRAG preserves foundational capabilities of the backbone while maintaining a favorable efficiency-performance trade-off on general text encoding and generative tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00871 — 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 2026-11-03T18:09:53.546Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).