Manifold-Aware Distance Metrics in Dense Retrieval Across Extended Context Windows

Abstract

Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: How does the performance of manifold-aware distance metrics in dense passage retrieval scale with increasing context window sizes beyond 512 tokens on Natural Questions and HotpotQA benchmarks. Dense Passage Retrieval (DPR) typically relies on Euclidean or cosine distance to measure query-passage relevance in embedding space, which is effective when embeddings lie on a linear manifold. However, our experiments across DPR benchmarks suggest that embeddings often lie on. 13 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 4.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the performance of manifold-aware distance metrics in dense passage retrieval scale with increasing context window sizes beyond 512 tokens on Natural Questions and HotpotQA benchmarks?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance