@article{flaworartifactrethinkingpromptsensitivit, title = {Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs}, author = {Andong Hua and Kenan Tang and Chenhe Gu and Jindong Gu and Eric Wong and Yao Qin}, year = {2025}, eprint = {2509.01790}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.01790}, }