CHSR-RRF：面向教育RAG的课程门控混合检索框架与泄漏感知基准
原标题：CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG
AI 摘要
CHSR-RRF 是一个面向教育领域 RAG 的课程门控混合检索框架，在检索前应用元数据约束，结合稀疏与稠密检索及倒数排名融合，以减少课程泄漏。作者还提出了 CERB 基准（126 个案例），实验显示预检索门控将泄漏率降低 4.6 倍，而检索后过滤会导致召回率归零。研究表明教育检索应视为约束选择问题，在候选池构建时强制有效性。
正文节选
CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG Abstract 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 leaka