@article{investigatingdatacontaminationforpre, title = {Investigating Data Contamination for Pre-training Language Models}, author = {Minhao Jiang and Ken Ziyu Liu and Ming Zhong and Rylan Schaeffer and Siru Ouyang and Jiawei Han and Sanmi Koyejo}, year = {2024}, eprint = {2401.06059}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.06059v1}, }