@article{hellaswagproalargescalebilingual,
  title = {HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning},
  author = {Xiaoyuan Li and Moxin Li and Rui Men and Yichang Zhang and Keqin Bao and Wenjie Wang and Fuli Feng and Dayiheng Liu and Junyang Lin},
  year = {2025},
  eprint = {2502.11393},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.11393v1},
}