How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework

Zi Liang, Liantong Yu, Shiyu Zhang, Qingqing Ye, Haibo Hu

BibTeX
@inproceedings{liang2026how,
  author = {Zi Liang and Liantong Yu and Shiyu Zhang and Qingqing Ye and Haibo Hu},
  title = {{How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2026},
  doi = {10.1609/aaai.v40i44.41098},
}
Figure