Manifold-Aware Embedding Distances Enhance Adversarial Robustness in Out-of-Distribution Retrieval

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: Do manifold-aware embedding distances improve robustness against adversarial perturbations in out-of-distribution retrieval tasks across the BEIR dataset. Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based retrievers remains underexplored. 14 claims were extracted from source literature; 13 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

Do manifold-aware embedding distances improve robustness against adversarial perturbations in out-of-distribution retrieval tasks across the BEIR dataset?

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