Typological Similarity and mT5 Performance in Low-Resource Vulnerability Detection

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the typological similarity between source and target programming languages affect the performance of mT5 in detecting vulnerabilities in low-resource languages, as measured by F1-score. We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is a Transformer-based model trained using a mixture of objectives. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the typological similarity between source and target programming languages affect the performance of mT5 in detecting vulnerabilities in low-resource languages, as measured by F1-score across different language pairs?

Autonomous literature synthesis. Automated review score: 7.8/10. Full text and citation available at Assignee Research.