Dense-Sparse Retrieval Augmentation Impact on Code Generation Accuracy and Latency

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the combination of dense and sparse retrieval augmentation strategies affect the HumanEval pass@1 score and latency in code generation tasks when scaling the number of retrieved documents. 10 claims were extracted from source literature; 9 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 does the combination of dense and sparse retrieval augmentation strategies affect the HumanEval pass@1 score and latency in code generation tasks when scaling the number of retrieved documents from 5 to 50?

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