paperAugust 2026Unreviewed

Auditing Cross-Lingual Fairness in Language Model Watermarking

Alexander Nemecek, Osama Zafar, Debargha Ganguly, Vikash Singh, Vipin Chaudhary, Erman Ayday

Abstract

Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measurements. Multilingual deployment exposes evaluation-design choices that are inconsequential on English but determine conclusions cross-lingually. We propose an evaluation framework with four components: detection thresholds calibrated empirically per deployment context, a threshold-independent companion measurement that dis

Cite

@misc{nemecek2026auditing,
  title = {{Auditing Cross-Lingual Fairness in Language Model Watermarking}},
  author = {Alexander Nemecek and Osama Zafar and Debargha Ganguly and Vikash Singh and Vipin Chaudhary and Erman Ayday},
  year = {2026},
  month = aug,
  eprint = {2608.20047},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/25ee21ef07b6282273f369076f9000bef569ad0a}
}