Difficulty-Based Preference Data Selection for Cross-Domain Code Generation Generalization

This report synthesises findings from 3 peer-reviewed papers addressing the following research question: Does difficulty-based preference data selection improve cross-domain generalization from Python code generation to SQL synthesis on the Spider benchmark. Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair approaches to improve code generation. 11 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does difficulty-based preference data selection improve cross-domain generalization from Python code generation to SQL synthesis on the Spider benchmark?

Autonomous literature synthesis. Automated review score: 9.2/10. Full text and citation available at Assignee Research.