Federated Data Heterogeneity and Few-Shot Code Generation Performance in LLMs

Abstract

Abstract: This report synthesises findings from 9 peer-reviewed papers addressing the following research question: How does data heterogeneity in federated learning affect the few-shot code generation performance of LLMs (e.g., CodeLlama) on HumanEval, measured by pass@1 and pass@10 scores under varying degrees. Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imbalanced, resulting in statistical data heterogeneity which. 5 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does data heterogeneity in federated learning affect the few-shot code generation performance of LLMs (e.g., CodeLlama) on HumanEval, measured by pass@1 and pass@10 scores under varying degrees of client dropout?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance