Adversarial Fine-Tuning Effects on LLM Code Generation Benchmark Performance

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does fine-tuning on adversarially perturbed code datasets impact pass@1 scores on the original HumanEval and MBPP benchmarks compared to standard supervised fine-tuning. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does fine-tuning on adversarially perturbed code datasets impact pass@1 scores on the original HumanEval and MBPP benchmarks compared to standard supervised fine-tuning?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.