@article{plumpreferencelearningplustestcases,
  title = {$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases},
  author = {Dylan Zhang and Shizhe Diao and Xueyan Zou and Hao Peng},
  year = {2024},
  eprint = {2406.06887},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.06887v4},
}