@article{pacostpairedconfidencesignificancetestin, title = {PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models}, author = {Huixuan Zhang and Yun Lin and Xiaojun Wan}, year = {2024}, eprint = {2406.18326}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.18326v1}, }