Manifold-Aware Distance Metrics Enhance Robustness in Dense Retrievers Under Distribution Shift

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: Does integrating manifold-aware distance metrics into the training objective improve the robustness of dense retrievers against adversarial perturbations in out-of-distribution query settings. Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does integrating manifold-aware distance metrics into the training objective improve the robustness of dense retrievers against adversarial perturbations in out-of-distribution query settings?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.