# Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora

arXiv: https://arxiv.org/abs/2610.10170 · HTML: https://mlsanity.com/paper/2610.10170/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 7 of 7)

- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis](https://mlsanity.com/paper/2505.21700/) (2025)
- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval](https://mlsanity.com/paper/2602.16974/) (2026)
- [A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity](https://mlsanity.com/paper/2603.06976/) (2026)
- [Hierarchical Re-ranker Retriever (HRR)](https://mlsanity.com/paper/2503.02401/) (2025)

## Abstract (arXiv)

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 shuffled across documents. We score retrieval with a coverage-aware nDCG and test four pre-registered contrasts via document-clustered bootstrap with Holm correction, on two distant corpora: 200 Wikipedia Featured Articles (951 queries) and 1,585 QASPER papers (4,303 questions). Organization helps, and the cause is content, not tokens: structure-aligned chunks with real heading paths beat contextualized fixed windows (+0.022 / +0.012 cov-nDCG@10) and the placebo (+0.010 / +0.016). Naive two-stage hierarchical retrieval hurts (-0.033 / -0.015), traceable to first-stage section recall. Gold structure beats LLM-induced structure on Wikipedia but not on QASPER. Effects are small (dz 0.06-0.11) but Holm-significant and consistent across corpora.