@article{samemeaningdifferentscoreslexicalandsynt,
  title = {Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation},
  author = {Bogdan Kostić and Conor Fallon and Julian Risch and Alexander Löser},
  year = {2026},
  eprint = {2602.17316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.17316},
}