Comparative Analysis of Retrieval-Augmented Few-Shot Prompting and Fine-Tuned CodeBERT on Big-Vul Robustness

Few-shot prompting has emerged as a practical alternative to fine-tuning for leveraging the capabilities of large language models (LLMs) in specialized tasks. However, its effectiveness depends heavily on the selection and quality of in-context examples, particularly in complex domains. In this work, we examine retrieval-augmented prompting as a strategy to improve few-shot performance in code vulnerability detection, where the goal is to identify one or more security-relevant weaknesses present in a given code snippet from a predefined set of vulnerability categories. We perform a systematic

Research goal: How does retrieval-augmented few-shot prompting with Llama-3.1-8B compare to fine-tuned CodeBERT in terms of false positive rates and robustness against adversarial code perturbations on the Big-Vul dataset?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.8/10.