Multi-Scale Contrastive Pre-Training for Adversarial Robustness in Large Language Models

Abstract

Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: To what extent does multi-scale contrastive pre-training improve the robustness of large language models against adversarial text perturbations as measured by accuracy drop on GLUE benchmark tasks. Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

To what extent does multi-scale contrastive pre-training improve the robustness of large language models against adversarial text perturbations as measured by accuracy drop on GLUE benchmark tasks?

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