Metraipolis › archive › dc_c827449aa16e
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving — arXiv:2609.11209
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11209
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:44:23.113Z
- SHA-256 of the archived text
b2a96c5305db6948aa41ba13242ee4fcd690d52aa412fd9f57c2b0d2abe503a6- Stable URL of this page
https://metraipolis.com/documento/dc_c827449aa16e
How to cite
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving — arXiv:2609.11209 — arXiv (en), https://arxiv.org/abs/2609.11209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c827449aa16e (Metraipolis archive dc_c827449aa16e, sha256 b2a96c5305db6948aa41ba13242ee4fcd690d52aa412fd9f57c2b0d2abe503a6)
BibTeX
@misc{dcc827449aa16e,
title = {REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving — arXiv:2609.11209},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11209},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c827449aa16e; sha256 b2a96c5305db6948aa41ba13242ee4fcd690d52aa412fd9f57c2b0d2abe503a6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved documents, but longer contexts increase latency, key-value (KV) cache memory, and token cost. Post-retrieval compression can reduce this cost, yet existing compressors often operate independently for each query, rely on auxiliary models or rewriting, and introduce online overhead that can offset the benefit of shorter prompts. We revisit RAG compression from a data-mining perspective by aggregating historical query--document--model interactions into reusable evidence views. We first show that modern compressors have unstable gains over simple truncation and can add substantial inference-time latency. We then propose Reusable Evidence View Aggregation (REVA), a framework that mines the target generator's historical attention traces into a document-keyed, budget-agnostic score store. REVA maps token-level attention to readable word units, aggregates importance across repeated document accesses, and renders budget-specific plain-text views that preserve document order and the standard RAG interface. Across four representative benchmarks and modern LLMs, REVA improves generation quality by 1.0--5.8 points over existing advances, while reducing compression overhead by a factor of 5.3 to 15.6, adding less than 40 ms of latency. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.11209 — 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 2026-10-16T05:23:57.041Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).