通过共现聚类重组织知识库，提升企业级RAG会话检索覆盖率
One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
- 基于共现关系聚类重构知识库，查询时扩展邻域候选
- 会话覆盖率达58%，较原方法提升17个百分点
- 适用于企业客服等连续问答场景，适配多种模型与领域
当前RAG系统针对单个查询优化检索，但企业用户常提出一系列语义关联的连续问题。我们发现，单次检索仅能满足41%的会话级信息需求。为此，论文提出离线使用共现感知聚类重组知识库，并在查询时通过簇邻域扩展候选。在包含6221篇企业支持文档的WixQA数据集上，该方法将单查询会话覆盖率提升至58%（绝对提升17%，95%置信区间[14.1, 20.4]），实现70%覆盖所需的检索调用减少34%，知识库压缩至原大小的20%，且在四种嵌入模型和六个功能领域中表现一致。论文主张应以会话级覆盖率而非单查询召回率作为企业RAG评估主指标。
原文摘要 · Abstract (English)
RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base covers only 41% of a user's session-level information need. To close this gap, we reorganize the KB offline using co-occurrence-aware clustering and expand retrieval candidates through cluster neighborhoods at query time. On WixQA (6,221 enterprise support articles), our method raises single-query session coverage to 58% (+17% absolute; 95% CI: [14.1, 20.4]), reduces retrieval calls to 70% coverage by 34%, and compresses the KB to 20% of its original size, all consistently across four embedding models and six functional domains. We argue that session-level coverage, not single-query recall, should be the primary metric for enterprise RAG evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。