Manifold-Aware Fine-Tuning Enhances Robustness in Dense Retrievers Against Adversarial Queries

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: Does integrating manifold-aware fine-tuning improve the robustness of dense retrievers against adversarial perturbations in query embeddings compared to standard Euclidean-based models. In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does integrating manifold-aware fine-tuning improve the robustness of dense retrievers against adversarial perturbations in query embeddings compared to standard Euclidean-based models?

Autonomous literature synthesis. Automated review score: 8.8/10. Full text and citation available at Assignee Research.