Metraipolis › archive › dc_23ea74deadfe

TripPattern: A Pattern-based Text Watermarking Method for Large Language Models — arXiv:2609.12472

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12472
License (as archived): CC0-1.0
Archived: 2026-10-16T03:02:47.142Z
SHA-256 of the archived text: 461864bd71ee57a81a8d6b8863b2be2ebe61100a219da7565debfb5cd90009c1
Stable URL of this page: https://metraipolis.com/documento/dc_23ea74deadfe

How to cite

TripPattern: A Pattern-based Text Watermarking Method for Large Language Models — arXiv:2609.12472 — arXiv (en), https://arxiv.org/abs/2609.12472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23ea74deadfe (Metraipolis archive dc_23ea74deadfe, sha256 461864bd71ee57a81a8d6b8863b2be2ebe61100a219da7565debfb5cd90009c1)

BibTeX

@misc{dc23ea74deadfe,
  title = {TripPattern: A Pattern-based Text Watermarking Method for Large Language Models — arXiv:2609.12472},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12472},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23ea74deadfe; sha256 461864bd71ee57a81a8d6b8863b2be2ebe61100a219da7565debfb5cd90009c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text watermarking techniques have gained significant attention for identifying machine-generated text and mitigating risks from large language models (LLMs). Existing methods typically divide an LLM's vocabulary into green and red tokens, but encouraging generation toward green tokens can reduce text quality and naturalness. To address this, we propose TripPattern, a watermarking framework that formulates text watermarking as a pattern-based matching task using three vocabulary partitions. TripPattern divides the vocabulary into one neutral group and two pattern groups. During generation, the model alternates token selection between the two pattern groups to embed detectable patterns, while neutral tokens are selected independently to improve flexibility and preserve naturalness. For detection, TripPattern uses pattern-based statistical tests that provide interpretable p-values by measuring how often adjacent tokens alternate between the pattern groups. Theoretical analysis and empirical evaluations on four multilingual datasets show that TripPattern maintains LLM generation quality while achieving robust watermark detectability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12472 — 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 2026-10-16T02:51:27.799Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).