Scaling Model Size and Adversarial Robustness in Multilingual Dialogue Act Classification

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the scaling of model size (e.g., XGLM-564M vs. XGLM-1.6B) affect adversarial robustness in dialogue act classification across different educational levels and languages, measured by standard. 10 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the scaling of model size (e.g., XGLM-564M vs. XGLM-1.6B) affect adversarial robustness in dialogue act classification across different educational levels and languages, measured by standard benchmark datasets like DAST or MultiWOZ?

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