Co-Augmentation Training Enhances Code Generation Stability Against Syntax-Preserving Attacks

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: To what extent does co-augmentation training improve the alignment stability of code generation models against syntax-preserving adversarial attacks as measured by pass@k scores on the HumanEval. This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. 15 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 6.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

To what extent does co-augmentation training improve the alignment stability of code generation models against syntax-preserving adversarial attacks as measured by pass@k scores on the HumanEval dataset?

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