Counterfactual Text Augmentation and Adversarial Robustness in Multimodal VQA Models

Abstract

Abstract: This report synthesises findings from 6 peer-reviewed papers addressing the following research question: How does counterfactual text augmentation impact the adversarial robustness accuracy of multimodal VQA models on the VQA-CP benchmark. In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn spurious correlations in the training set and achieve poor performance in out-ofdistribution test data. Some methods of generating counterfactual samples have been proposed to alleviate. 6 claims were extracted from source literature; 6 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 Question

How does counterfactual text augmentation impact the adversarial robustness accuracy of multimodal VQA models on the VQA-CP benchmark?

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