AI 中文总结
NativeScope是一种关系本地化检索方法，通过锚点和关系确定范围后排序，在200个受控文档和记忆记录上较实例级密集RAG有显著召回率提升，其增益主要来自关系范围确定。
AI 中文摘要
密集检索通常根据文本块与问题的语义相似度对其进行排序，这忽略了许多数据系统已存储的结构，包括章节归属、会话边界和原生顺序。我们提出NativeScope，一种针对具有已知锚点和关系的查询的“范围确定后排序”方法，将查询表示为q -> (A, r, B)。锚点A和关系r通过归属、之前或之后运算符选择原生单元，目标项B仅对与所选范围重叠的文本块进行排序。内部变体NS-FullQ使用完整问题对相同候选进行排序。我们在从QASPER和LongMemEval衍生的200个受控文档和记忆记录上，在1024-token预算下评估这两种方法。NativeScope对文档的原生单元召回率达89.28%，对记忆的召回率达72.50%，较实例级密集RAG分别提升42.75和22.00个百分点。NS-FullQ的召回率达87.78%和68.50%，其与NativeScope的差异无定论，表明主要增益来自关系范围确定而非更短的排序查询。在自动Top-1锚点下，记忆召回率降至35.50%。因此，NativeScope在锚点坐标和原生关系可靠时有效，但严格的范围确定会继承定位接口的错误。
英文摘要
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.
Comments14 pages, 4 figures, and 6 tables. Includes an appendix with reproduction information and an evidence inventory
