Manifold-Aware Metrics Enhance Recall in Dense Retrieval for Multi-Hop Reasoning

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does replacing Euclidean distance with manifold-aware metrics in dense retrieval affect Recall@1000 performance on multi-hop reasoning datasets like HotpotQA compared to standard DPR baselines. 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. 12 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 5.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does replacing Euclidean distance with manifold-aware metrics in dense retrieval affect Recall@1000 performance on multi-hop reasoning datasets like HotpotQA compared to standard DPR baselines?

Verification Level

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

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

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