FedDiverse Diversity-Driven Selection Accelerates CodeLlama Convergence on MBPP

This report synthesises findings from 1 peer-reviewed paper addressing the following research question: Does the diversity-driven selection in FedDiverse reduce the convergence rounds required for CodeLlama to achieve target accuracy on the MBPP dataset relative to federated averaging in heterogeneous. Large language models (LLMs) frequently generate defective outputs in code generation tasks, ranging from logical bugs to security vulnerabilities. While these generation failures are often treated as model-level limitations, empirical evidence increasingly traces their root. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does the diversity-driven selection in FedDiverse reduce the convergence rounds required for CodeLlama to achieve target accuracy on the MBPP dataset relative to federated averaging in heterogeneous settings?

Autonomous literature synthesis. Automated review score: 9.3/10. Full text and citation available at Assignee Research.