Liang, Zi, Liantong Yu, Zhang Shiyu, Qingqing Ye, and Haibo Hu. 2026. “How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (44):37636-44. https://doi.org/10.1609/aaai.v40i44.41098.