Abstract
Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Existing approaches typically embed signals by manipulating token generation probabilities. Despite their effectiveness, these methods inherently face a trade-off between detectability and text quality: the signal strength and randomness required for robust watermarking tend to degrade the performance of downstream tasks. In this paper, we design a novel embedding scheme that controls seed pools to facilitate diverse parallel generation of watermarked text. Based on that scheme, we propose WaterSearch, a sentence-level, search-based watermarking framework adaptable to a wide range of existing methods. WaterSearch enhances text quality by jointly optimizing two key aspects: 1) distribution fidelity and 2) watermark signal characteristics. Furthermore, WaterSearch is complemented by a sentence-level detection method with strong attack robustness. We evaluate our method on three popular LLMs across ten diverse tasks. Extensive experiments demonstrate that our method achieves an average performance improvement of 51.01\% over state-of-the-art baselines at a watermark detectability strength of 95\%. In challenging scenarios such as short text generation and low-entropy output generation, our method yields performance gains of 47.78\% and 36.47\%, respectively. Moreover, under different attack senarios including insertion, synonym substitution and paraphrase attasks, WaterSearch maintains high detectability, further validating its robust anti-attack capabilities. Our code is available at \href{this https URL}{this https URL}.
Abstract (translated)
水印技术是大型语言模型（LLMs）生成文本时的重要安全措施。通过在模型输出中嵌入可识别的信号，水印能够实现可靠的归属认定，并提升机器生成内容的安全性。现有方法通常通过调整令牌生成概率来嵌入这些信号。尽管这些方法有效，但它们内在地存在一个检测性和文本质量之间的权衡：为了使水印稳健可靠，所需的信号强度和随机性往往会降低下游任务的性能。 在本文中，我们设计了一种新的嵌入方案，该方案通过控制种子池来促进带水印文本的多样化并行生成。基于这一方案，我们提出了一种句子级、搜索式的水印框架WaterSearch，其适应于广泛现有的方法。WaterSearch 通过优化两个关键方面增强了文本质量：1）分布保真度；2）水印信号特性。 此外，WaterSearch 还配备了具有强大攻击抵御能力的句子级别检测方法。我们在三个流行的大型语言模型上进行了十项多样化任务上的评估。大量实验表明，在95% 的水印可检测强度下，我们的方法相比最先进的基准方法平均性能提高了51.01%。在诸如短文本生成和低熵输出生成等具有挑战性的场景中，该方法分别实现了47.78% 和36.47% 的性能提升。 此外，在包括插入、同义词替换以及改写攻击在内的不同攻击情景下，WaterSearch 维持了高检测性，进一步验证了其强大的抗攻击能力。我们的代码可在[此链接](this https URL)获得。
URL
https://arxiv.org/abs/2512.00837
