CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Junyan, Liu, Shuliang, Liu, Aiwei, Gao, Yubo, Li, Jungang, Gu, Xiaojie, Hu, Xuming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910917906661376
author Zhang, Junyan
Liu, Shuliang
Liu, Aiwei
Gao, Yubo
Li, Jungang
Gu, Xiaojie
Hu, Xuming
author_facet Zhang, Junyan
Liu, Shuliang
Liu, Aiwei
Gao, Yubo
Li, Jungang
Gu, Xiaojie
Hu, Xuming
contents Watermarking technology is a method used to trace the usage of content generated by large language models. Sentence-level watermarking aids in preserving the semantic integrity within individual sentences while maintaining greater robustness. However, many existing sentence-level watermarking techniques depend on arbitrary segmentation or generation processes to embed watermarks, which can limit the availability of appropriate sentences. This limitation, in turn, compromises the quality of the generated response. To address the challenge of balancing high text quality with robust watermark detection, we propose CoheMark, an advanced sentence-level watermarking technique that exploits the cohesive relationships between sentences for better logical fluency. The core methodology of CoheMark involves selecting sentences through trained fuzzy c-means clustering and applying specific next sentence selection criteria. Experimental evaluations demonstrate that CoheMark achieves strong watermark strength while exerting minimal impact on text quality.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality
Zhang, Junyan
Liu, Shuliang
Liu, Aiwei
Gao, Yubo
Li, Jungang
Gu, Xiaojie
Hu, Xuming
Computation and Language
Watermarking technology is a method used to trace the usage of content generated by large language models. Sentence-level watermarking aids in preserving the semantic integrity within individual sentences while maintaining greater robustness. However, many existing sentence-level watermarking techniques depend on arbitrary segmentation or generation processes to embed watermarks, which can limit the availability of appropriate sentences. This limitation, in turn, compromises the quality of the generated response. To address the challenge of balancing high text quality with robust watermark detection, we propose CoheMark, an advanced sentence-level watermarking technique that exploits the cohesive relationships between sentences for better logical fluency. The core methodology of CoheMark involves selecting sentences through trained fuzzy c-means clustering and applying specific next sentence selection criteria. Experimental evaluations demonstrate that CoheMark achieves strong watermark strength while exerting minimal impact on text quality.
title CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality
topic Computation and Language
url https://arxiv.org/abs/2504.17309