Causation

When Adaptive Depth Helps vs When Fixed-Depth Is Safer (Budget/Cap Guidance)

The paper's token-budget guidance is a dataset-aware conditional recommendation: adaptive retrieval can be useful when kk is small and token caps are loose (where its tight-budget pointwise gain on LectureBank-Full appears at k=4k=4); under strict token caps, the simpler fixed-depth hierarchical baseline is the safer descriptive default on LectureBank-Full, because adaptive contexts are longer on average and lose more under truncation. The recommendation is dataset-aware: it is supported on LectureBank-Full and is not supported on MOOC-CS, where the ΔR@k\Delta\text{R@}k curve stays near zero. It is framed as descriptive guidance rather than a multiplicity-corrected significance claim.

0

1

Updated 2026-05-17

Contributors are:

Who are from:

Tags

Science

Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls