@article{proberewriteevaluateaworkflowforreliable, title = {Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness}, author = {Lang Xiong and Nishant Bhargava and Jianhang Hong and Jeremy Chang and Haihao Liu and Vasu Sharma and Kevin Zhu}, year = {2025}, eprint = {2509.00591}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.00591}, }