@article{scalingreinforcementlearningforcontentmo,
  title = {Scaling Reinforcement Learning for Content Moderation with Large Language Models},
  author = {Hamed Firooz and Rui Liu and Yuchen Lu and Zhenyu Hou and Fangzhou Xiong and Xiaoyang Zhang and Changshu Jian and Zhicheng Zhu and Jiayuan Ma and Jacob Tao and Chaitali Gupta and Xiaochang Peng and Shike Mei and Hang Cui and Yang Qin and Shuo Tang and Jason Gaedtke and Arpit Mittal},
  year = {2025},
  eprint = {2512.20061},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.20061},
}