Text watermarking has emerged as an important technique for detecting
machine-generated text. However, existing methods can severely degrade text
quality due to arbitrary vocabulary partitioning, which disrupts the language
model's expressiveness and impedes textual coherence. To mitigate this, we
introduce XMark, a novel approach that capitalizes on text redundancy within
the lexical space. Specifically, XMark incorporates a mutually exclusive rule
for synonyms during the language model decoding process, thereby integrating
prior knowledge into vocabulary partitioning and preserving the capabilities of
language generation. We present theoretical analyses and empirical evidence
demonstrating that XMark substantially enhances text generation fluency while
maintaining watermark detectability. Furthermore, we investigate watermarking's
impact on the emergent abilities of large language models, including zero-shot
and few-shot knowledge recall, logical reasoning, and instruction following.
Our comprehensive experiments confirm that XMark consistently outperforms
existing methods in retaining these crucial capabilities of LLMs.

文本水印是一种重要的检测机器生成文本的技术。然而，现有方法可能会因为任意的词汇划分而严重降低文本质量，破坏了语言模型的表达能力并妨碍了文本的连贯性。为了减轻这一问题，我们介绍了一种新颖的方法 XMark，它利用词汇空间中的文本冗余。具体而言，XMark 在语言模型解码过程中引入了一种互相排斥的同义词规则，从而将先前的知识整合到词汇划分中，并保留了语言生成的能力。我们提供了理论分析和实证证据，表明 XMark 在提高文本生成流畅性的同时保持了水印的可检测性。此外，我们还研究了水印对大型语言模型的新能力的影响，包括零样本和少样本知识回忆、逻辑推理和指令跟踪。我们的综合实验证实，XMark 在保留 LLM 的这些关键能力方面始终优于现有方法。