Metraipolis › archive › dc_e67e49f3ff8b

NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor — arXiv:2610.12243

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12243
License (as archived)
CC0-1.0
Archived
2026-10-09T06:13:52.296Z
SHA-256 of the archived text
e5d94dcef61e6679affea72689f535e1a7a310a48398879a185e77c721fb71b0
Stable URL of this page
https://metraipolis.com/documento/dc_e67e49f3ff8b

How to cite

NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor — arXiv:2610.12243 — arXiv (en), https://arxiv.org/abs/2610.12243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e67e49f3ff8b (Metraipolis archive dc_e67e49f3ff8b, sha256 e5d94dcef61e6679affea72689f535e1a7a310a48398879a185e77c721fb71b0)
BibTeX
@misc{dce67e49f3ff8b,
  title = {NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor — arXiv:2610.12243},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12243},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e67e49f3ff8b; sha256 e5d94dcef61e6679affea72689f535e1a7a310a48398879a185e77c721fb71b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dense retrieval usually ranks text chunks by their semantic similarity to a question. This ignores structure that many data systems already store, including section membership, session boundaries, and native order. We propose NativeScope, a scope-then-rank method for queries with a known anchor and relation. It represents a query as q -> (A, r, B). The anchor A and relation r select native units through belonging, before, or after operators, and the target term B ranks only chunks that overlap the selected scope. An internal variant, NS-FullQ, ranks the same candidates with the full question. We evaluate both methods on 200 controlled document and memory records derived from QASPER and LongMemEval under a 1,024-token budget. NativeScope attains native-unit recall of 89.28 percent for documents and 72.50 percent for memories, improving over instance-wide Dense RAG by 42.75 and 22.00 percentage points. NS-FullQ reaches 87.78 percent and 68.50 percent; its differences from NativeScope are inconclusive, locating the primary gain in relational scoping rather than the shorter ranking query. With automatic Top-1 anchors, memory recall falls to 35.50 percent. NativeScope is therefore effective when anchor coordinates and native relations are reliable, but hard scoping inherits errors from the localization interface.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.12243 — 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 2026-10-09T05:47:15.511Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).