用句子间连贯性实现高质量文本水印，提升防伪能力。
CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality
- 通过模糊c均值聚类筛选连贯句子，结合下一句选择策略嵌入水印。
- 水印强度强，对文本质量影响极小，生成内容更流畅自然。
- 适合需要高保真生成与可追溯性的大模型应用，如新闻、报告生成。
文本水印技术用于追踪大语言模型生成内容的使用情况。句级水印在保持单句语义完整性的同时具备更强鲁棒性。然而，现有方法多依赖任意分句或生成过程嵌入水印，限制了可用句段数量，进而损害生成文本质量。为平衡高文本质量与强水印检测能力，本文提出CoheMark——一种基于句子间连贯关系的新型句级水印技术。其核心方法包括：利用训练好的模糊c均值聚类筛选句子，并施加特定的下一句选择准则。实验表明，CoheMark在维持极低文本质量损失的前提下，实现了强劲的水印强度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。