NativeScope：基于原生拓扑与正确锚点的关系局部化检索

View PDF HTML (experimental)

Abstract: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.

Comments:	14 pages, 4 figures, and 6 tables. Includes an appendix with reproduction information and an evidence inventory
Subjects:	Information Retrieval (cs.IR); Computation and Language (cs.CL)
Cite as:	arXiv:2610.12243 [cs.IR]
	(or arXiv:2610.12243v1 [cs.IR] for this version)
	https://doi.org/10.48550/arXiv.2610.12243 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Long Wang [view email]
[v1] Thu, 8 Oct 2026 16:21:51 UTC (2,606 KB)