Abstract
RAG systems rely on chunking, which destroys structural information in documents. Existing heading-based retrieval (Jeong et al., 2025) requires multiple LLM calls per document and returns sub-chunks within matched sections. We introduce ToC-guided page retrieval, which infers headings from visual formatting without LLM calls, embeds them as a parallel index, and loads full page sections.
Across 1,280 conditions on 8 enterprise documents (5 to 195 pages), we find:
- ToC is a significant main effect on answer quality (d = +0.41, p = 0.031), with the largest gains in completeness (+0.40) and usefulness (+0.40);
- Combined with answer-side verification, it outperforms query-side decomposition + verification (d = +0.32, p = 0.036);
- ToC contributes 20% of citations despite adding only 2.9 pages per query;
- Gains are directionally larger on longer documents (up to +1.50 on 118 pages), though the trend does not reach significance with 8 documents;
- A 480-condition sensitivity analysis finds no significant parameter effects (all p > 0.38), confirming defaults are near-optimal.
The contribution is both methodological (a new zero-LLM-cost retrieval algorithm) and empirical: factorial evidence that document-side, query-side, and answer-side enhancements are complementary, a three-way interaction not previously studied.
Blogger's Review: This research demonstrates how to effectively utilize document structural information in RAG systems. The proposed ToC-guided retrieval method not only reduces LLM call costs but also enhances answer quality, offering significant practical application value.