自条件位置HNSW：面向分块文档RAG系统的重叠感知检索方法与工业证据质量审计
Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit
AI总结：
提出自条件位置HNSW（SCP-HNSW），通过低维位置编码和两遍查询过程实现重叠感知检索，减少重复证据，并基于工业审计数据验证其有效性。
摘要：
分块文档检索是检索增强生成（RAG）系统的常见组件。文档被分割成重叠的块，嵌入，并使用近似最近邻搜索（如分层可导航小世界图HNSW）进行索引。重叠改善了边界覆盖，但引入了一个实际故障模式：top-k检索通常返回重复证据的相邻块，浪费提示预算。我们提出自条件位置HNSW（SCP-HNSW），这是一种轻量级修改，将低维位置代码附加到块嵌入，并使用两遍查询过程来估计和应用查询特定的文档位置先验。SCP-HNSW保持HNSW图构建和遍历不变，同时为最终上下文构建添加了一个可审计的最小索引间隙选择器。我们还集成了用于生成证据质量的工业审查工件：一个包含318个完全标记审查的770条文本证据审计，以及一个包含350个评级的70例OCR审计。文本审计显示，770个预计审查中有574个被评为3/5，只有39个落在1-2范围内，叙述性审查者细节比结构化问题标志出现得更频繁。OCR审计显示，切片级通过率从干净聊天截图的95%到手写/模糊捕获的45%不等，一致性中等至强。这些结果激励了重叠感知、审计友好的RAG检索，并确定了因果性能声明所需的剩余受控检索消融。
英文摘要：
Chunked-document retrieval is a common component of retrieval-augmented generation (RAG) systems. Documents are split into overlapping chunks, embedded, and indexed with approximate nearest-neighbor search such as hierarchical navigable small world graphs (HNSW). Overlap improves boundary coverage but induces a practical failure mode: top-k retrieval often returns near-adjacent chunks that repeat evidence and waste prompt budget. We propose Self-Conditioned Positional HNSW (SCP-HNSW), a lightweight modification that appends a low-dimensional positional code to chunk embeddings and uses a two-pass query procedure to estimate and apply a query-specific document-position prior. SCP-HNSW leaves HNSW graph construction and traversal unchanged while adding an auditable minimum-index-gap selector for final context construction. We also integrate industrial review artifacts for generated evidence quality: a 770-review text-evidence audit with 318 fully labeled reviews and a 70-case OCR audit with 350 ratings. The text audit shows that 574 of 770 projected reviews are rated 3/5, only 39 fall in the 1-2 range, and narrative reviewer detail appears much more often than structured issue flags. The OCR audit shows slice-level pass rates from 95% for clean chat screenshots to 45% for handwritten/blurry captures, with moderate to strong agreement. These results motivate overlap-aware, audit-friendly RAG retrieval and identify the remaining controlled retrieval ablations needed for causal performance claims.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
