AI 中文总结
本研究提出一种查询感知的预生成分流方法，通过四维评分、族聚合及路由机制，对RAG检索页面进行分类，并设计验证计划以提升风险覆盖，而非直接估计部署效果。
AI 中文摘要
检索增强生成（RAG）流水线可能忽略来源与查询之间的实质性关联。我们研究了一个生成前的分流层，该层将此关联视为查询相关的。该方法将规范查询族路由至增强审查，并将检索到的页面分配为通过、情境化、排除或审查。它结合了四维页面评分、排名折扣的族聚合、意图保持的查询变异以及族保留路由器。一个包含200个真实URL的单编码试点提供了临时校准锚点；一个包含20,000行且带有合成领域标识符的场景支持受控工作负载分析。一个预言机页面门限为未来的学习分类器定义了风险覆盖目标。评估表明，页面级频率为何不能替代族级暴露，并量化了校准如何改变场景激活。注释可靠性尚未测量，合成排名忽略了真实检索动态。结果是一种可审计的分流方法和验证计划，而非对部署审查工作负载、实时网络流行率或下游答案质量提升的估计。
英文摘要
Retrieval-augmented generation (RAG) pipelines may omit a source's material relationship to the query. We study a pre-generation triage layer that treats this relationship as query dependent. The method routes canonical query families for enhanced review and assigns retrieved pages to pass, contextualize, exclude, or review. It combines a four-dimension page score, rank-discounted family aggregation, intent-preserving query mutations, and a family-held-out router. A single-coded pilot of 200 real URLs supplies provisional calibration anchors; a 20,000-row scenario with synthetic domain identifiers supports controlled workload analysis. An oracle page gate defines a risk-coverage target for a future learned classifier. The evaluation shows why page-level frequency cannot substitute for family-level exposure and quantifies how calibration changes scenario activation. Annotation reliability remains unmeasured, and synthetic rankings omit real retrieval dynamics. The result is an auditable triage method and validation plan, not an estimate of deployed review workload, live-Web prevalence, or downstream answer-quality gains.
Comments6 pages, 6 figures, 5 tables. Accepted at CAIT 2026
