Research
More Context, Same Budget: Dual-Bounded Relational Recall Beyond Top-K Retrieval
arXiv:2608.18448v1 Announce Type: cross Abstract: More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requir
arXiv:2608.18448v1 Announce Type: cross Abstract: More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requires by following relationships between evidence that flat top-k ranking leaves behind. We test that proposition with Dual-Bounded Relational Recall (DBRR), which allocates a fixed retrieval budget between relevance-selected seeds and bounded graph-adjacent context, against matched flat top-k retrieval using the same relevance-ranking stage and the same maximum number of retrieval units and tokens. The outcome is complete recovery of the official HotpotQA supporting-evidence set for each question. Across 7,405 FullWiki questions, the Primary DBRR allocation increased complete supporting-evidence recovery by 23.8 percentage points over its matched flat baseline (paired risk difference 0.2377; question-level bootstrap 95% interval 0.2269 to 0.2489). It improved 1,952 questions, tied on 5,261, and harmed 192. Bridge questions drove the effect, with a 28.7-point increase; comparison questions showed a smaller 4.2-point difference. In a prespecified, evaluation-only diagnostic population, real relationships also outperformed random-neighbor and degree-preserving shuffled-graph controls. The result is straightforward: under the same context budget, complete-evidence retrieval depends not only on which items rank highest, but on how context is allocated around them. Relational allocation recovered complete evidence sets that flat top-k retrieval left incomplete.
Related
- What Survives Into Context: A Diagnostic for Budget-Constrained Multi-Hop RAG and When Submodular Evidence Packing Improves It
- Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
- Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
- HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
Source: arXiv cs.CL | 2026-08-20