Multi-Language LLM Alignment with Human Feedback Enhances Robustness in Adversarial Code Generation

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the alignment of multi-language LLMs with human feedback (e.g., using DPO or RLAIF) improve their robustness on adversarial code generation benchmarks like CodeGenBench, evaluated via BLEU. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the alignment of multi-language LLMs with human feedback (e.g., using DPO or RLAIF) improve their robustness on adversarial code generation benchmarks like CodeGenBench, evaluated via BLEU and code execution success rates?

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