Sequential Fine-Tuning and Multi-Task Learning Effects on Codestral Zero-Shot Vulnerability Detection

This report synthesises findings from 6 peer-reviewed papers addressing the following research question: How does sequential fine-tuning on specific CWE categories affect Codestral's zero-shot accuracy on unseen vulnerability types in the Juliet test suite compared to multi-task learning. Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the framework's default language (usually Python). In this article, we study the impact of using. 5 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does sequential fine-tuning on specific CWE categories affect Codestral's zero-shot accuracy on unseen vulnerability types in the Juliet test suite compared to multi-task learning?

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