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

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

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.