Alignment-Weighted DPO Robustness Scaling Across LLaMA-2 Model Variants

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does the robustness of alignment-weighted DPO scale across LLaMA-2 variants (7B, 13B, 70B) on adversarial TruthfulQA prompts compared to standard DPO alignment. Adversarial robustness of deep learning models has gained much traction in the last few years. Various attacks and defenses are proposed to improve the adversarial robustness of modern-day deep learning architectures. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 4.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the robustness of alignment-weighted DPO scale across LLaMA-2 variants (7B, 13B, 70B) on adversarial TruthfulQA prompts compared to standard DPO alignment?

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