Zero-Shot Visual Language Models vs. Fine-Tuned Code-Specific Multimodal Models on Unseen CWE Benchmarks

This report synthesises findings from 4 peer-reviewed papers addressing the following research question: How do zero-shot Visual Language Models like Flamingo compare to fine-tuned code-specific multimodal models in terms of accuracy on unseen CWE categories in benchmarks like CWESec and SARD. Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. 17 claims were extracted from source literature; 16 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How do zero-shot Visual Language Models like Flamingo compare to fine-tuned code-specific multimodal models in terms of accuracy on unseen CWE categories in benchmarks like CWESec and SARD?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.