Directional Preference Alignment Robustness to Adversarial Inputs in Code Generation

Abstract

Abstract: This report synthesises findings from 1 peer-reviewed paper addressing the following research question: How robust is the Directional Preference Alignment framework to adversarial or edge-case inputs in code generation tasks compared to RLHF, as measured by accuracy on a curated subset of HumanEval. The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to. 5 claims were extracted from source literature; 5 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

How robust is the Directional Preference Alignment framework to adversarial or edge-case inputs in code generation tasks compared to RLHF, as measured by accuracy on a curated subset of HumanEval with perturbed or ambiguous prompts?

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