CHSR-RRF：一种用于教育检索增强生成（RAG）的课程门控混合检索框架，结合了互反秩融合与感知漏检的基准测试
CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG
浏览论文内容
中文总结 AI 辅助
本研究针对教育RAG的课程漏检问题，提出CHSR-RRF框架，结合检索前元数据约束、混合检索与互反秩融合，构建126案例的CERB基准，实验验证其可显著降低漏检率且保留召回率。
中文摘要 AI 辅助
检索增强生成（RAG）正越来越多地应用于教育问答领域，但标准检索器仅优化主题相关性，未强制要求课程有效性。在学校场景中，一段文本可能具有相关性，但如果来自错误的学科、年级或考试语境则不合适；我们将这种失败模式称为课程漏检。我们提出CHSR-RRF，这是一种课程门控混合检索框架，在检索前应用元数据约束，随后结合稀疏与密集搜索，并采用互反秩融合和确定性重排序。我们还引入CERB，这是一个包含126个案例的课程约束检索基准，具有层级感知相关性标签和明确的漏检标注。在61个案例的试点测试中，检索前的门控将漏检率降低了4.6倍（p<0.001），同时保留了排序召回率；而在检索后应用相同约束会使召回率和精确范围成功率降至零（p=0.039）。完整基准的下界分析进一步显示，许多剩余失败源于语料库和元数据的缺口，而非仅检索设计。这些结果表明，结构化教育领域的检索应被视为约束选择，需在形成候选池时而非排序后强制有效性。
英文摘要
Retrieval-augmented generation (RAG) is increasingly used in educational question answering, but standard retrievers optimize topical relevance without enforcing curriculum validity. In school settings, a passage can be relevant yet inappropriate if it comes from the wrong subject, level, or examination context; we call this failure mode curriculum leakage. We present CHSR-RRF, a curriculum-gated hybrid retrieval framework that applies metadata constraints before retrieval, then combines sparse and dense search with reciprocal rank fusion and deterministic reranking. We also introduce CERB, a 126-case benchmark for curriculum-constrained retrieval with hierarchy-aware relevance labels and explicit leakage annotations. On a 61-case pilot, pre-retrieval gating reduces leakage by 4.6x ($p<0.001$) while preserving ranked recall, whereas applying the same constraints after retrieval collapses recall and exact-scope success to zero ($p=0.039$). A full-benchmark lower-bound analysis further shows that many remaining failures arise from corpus and metadata gaps rather than retrieval design alone. These results show that retrieval in structured educational domains should be treated as constrained selection, with validity enforced when the candidate pool is formed rather than after ranking.
