Metraipolis › archive › dc_5ec8efa8d6c2

Auditing Cross-Lingual Fairness in Language Model Watermarking — arXiv:2608.20047

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20047
License (as archived)
CC0-1.0
Archived
2026-10-18T11:39:20.263Z
SHA-256 of the archived text
771b20a4ad066259e661ca00edf97a4a49343afb5e00d28916e25d04f6452b86
Stable URL of this page
https://metraipolis.com/documento/dc_5ec8efa8d6c2

How to cite

Auditing Cross-Lingual Fairness in Language Model Watermarking — arXiv:2608.20047 — arXiv (en), https://arxiv.org/abs/2608.20047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ec8efa8d6c2 (Metraipolis archive dc_5ec8efa8d6c2, sha256 771b20a4ad066259e661ca00edf97a4a49343afb5e00d28916e25d04f6452b86)
BibTeX
@misc{dc5ec8efa8d6c2,
  title = {Auditing Cross-Lingual Fairness in Language Model Watermarking — arXiv:2608.20047},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20047},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ec8efa8d6c2; sha256 771b20a4ad066259e661ca00edf97a4a49343afb5e00d28916e25d04f6452b86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 distinguishes calibration failures from detection failures, three disjoint quality measurement paradigms (distributional, paired-semantic, and reference-perplexity), and a generalized-entropy decomposition of cross-language disparity over a typological family partition. Applied to six watermarking schemes, three open-weight generators, eleven languages spanning four scripts and eight typological families, and both base and instruction-tuned regimes, the framework reveals failure modes that single-language single-paradigm evaluation cannot surface. Across detection and quality, observed disparity is predominantly between-family on the typological partition, indicating that cross-lingual fairness gaps in watermarking are structural to language properties rather than idiosyncratic to particular languages.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.20047 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T11:38:27.924Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).