@article{sparselfplaywithtreesearchrefinementto,
  title = {SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models},
  author = {Jiale Cheng and Xiao Liu and Cunxiang Wang and Xiaotao Gu and Yida Lu and Dan Zhang and Yuxiao Dong and Jie Tang and Hongning Wang and Minlie Huang},
  year = {2024},
  eprint = {2412.11605},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.11605v1},
}