Integrated Decision Gradients and Attention Rollout Robustness Under Adversarial Text Perturbations

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does the robustness of Integrated Decision Gradients compare to Attention Rollout in maintaining feature attribution consistency under adversarial text perturbations across standard NLP benchmark. Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these models can be challenged by carefully. 15 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.1/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the robustness of Integrated Decision Gradients compare to Attention Rollout in maintaining feature attribution consistency under adversarial text perturbations across standard NLP benchmark datasets?

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