arXiv:2610.10170 · RAG 检索增强
Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
文档结构是否有助于稠密检索？跨两个语料库的四种机制的安慰剂对照消融
Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
- 类型：arxiv
- 标识：2610.10170
- 链接：http://arxiv.org/abs/2610.10170v1
- 主分类：rag
- 形态：method
- TLDR：Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval. Separate studies support each on different corpora, embedders, and metrics, and none control for a shared confound: any text prepended to a chunk perturbs its embedding. We present a mechanism-isolating ablation testing all four treatments under one protocol, matching chunk sizes across conditions and adding a semantically null placebo---heading paths that are structurally valid but shuf
- 待LLM分类：否
- 标题中文：文档结构是否有助于稠密检索？跨两个语料库的四种机制的安慰剂对照消融
- TLDR中文：检索增强生成系统日益依赖文档结构处理：结构对齐分块、LLM 生成的块上下文、标题路径元数据，以及分层两阶段检索。各自研究在不同语料、嵌入器和指标上支持各自方法，但没有一项控制了共同混杂因素：在块前添加任何文本都会扰动其嵌入。我们提出机制隔离的消融方法，在同一协议下测试全部四种处理，跨条件匹配块大小，并加入一个语义为空的安慰剂——结构上有效但被打乱
- 来源文件：
- /inbox/tom/_candidates/2026-10-09-agent-rag-longcontext-candidates.json