@misc{nie2025uqassessinglanguagemodels,
  title = {UQ: Assessing Language Models on Unsolved Questions},
  author = {Nie, Fan and Liu, Ken Ziyu and Wang, Zihao and Sun, Rui and Liu, Wei and Shi, Weijia and Yao, Huaxiu and Zhang, Linjun and Ng, Andrew Y. and Zou, James and Koyejo, Sanmi and Choi, Yejin and Liang, Percy and Muennighoff, Niklas},
  year = {2025},
  eprint = {2508.17580},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2508.17580}
}

@article{liu2025language,
  title = {Language Models May Verbatim Complete Text They Were Not Explicitly Trained On},
  author = {Liu, Ken Ziyu and Choquette-Choo, Christopher A and Jagielski, Matthew and Kairouz, Peter and Koyejo, Sanmi and Liang, Percy and Papernot, Nicolas},
  journal = {arXiv preprint arXiv:2503.17514},
  year = {2025}
}

@article{huang2025exploring,
  title={Exploring and mitigating adversarial manipulation of voting-based leaderboards},
  author={Huang, Yangsibo and Nasr, Milad and Angelopoulos, Anastasios and Carlini, Nicholas and Chiang, Wei-Lin and Choquette-Choo, Christopher A and Ippolito, Daphne and Jagielski, Matthew and Lee, Katherine and Liu, Ken Ziyu and others},
  journal={arXiv preprint arXiv:2501.07493},
  year={2025}
}

@article{liu2024unlearning,
  title = {Machine unlearning in 2024},
  author = {Liu, Ken Ziyu},
  journal = {Stanford Computer Science},
  year = {2024},
  month = {May},
  url = {https://ai.stanford.edu/~kzliu/blog/unlearning},
}

@article{jiang2024investigating,
  title={Investigating Data Contamination for Pre-training Language Models},
  author={Jiang, Minhao and Liu, Ken Ziyu and Zhong, Ming and Schaeffer, Rylan and Ouyang, Siru and Han, Jiawei and Koyejo, Sanmi},
  journal={arXiv preprint arXiv:2401.06059},
  year={2024}
}

@inproceedings{liu2022privacy,
  title={On Privacy and Personalization in Cross-Silo Federated Learning},
  author={Liu, Ziyu and Hu, Shengyuan and Wu, Zhiwei Steven and Smith, Virginia},
  booktitle={Neural Information Processing Systems (NeurIPS)},
  year={2022}
}

@article{agarwal2021skellam,
  title={The Skellam Mechanism for Differentially Private Federated Learning},
  author={Agarwal, Naman and Kairouz, Peter and Liu, Ziyu},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  pages={5052--5064},
  year={2021}
}

@inproceedings{kairouz2021distributed,
  title={The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation},
  author={Kairouz, Peter and Liu, Ziyu and Steinke, Thomas},
  booktitle={International Conference on Machine Learning},
  pages={5201--5212},
  year={2021},
  organization={PMLR}
}