The strong general capabilities of Large Language Models (LLMs) bring potential ethical risks if they are unrestrictedly accessible to malicious users. Token-level watermarking inserts watermarks in the generated texts by altering the token probability distributions with a private random number generator seeded by its prefix tokens. However, this watermarking algorithm alters the logits during generation, which can lead to a downgraded text quality if it chooses to promote tokens that are less relevant given the input. In this work, we propose to improve the quality of texts generated by a watermarked language model by Watermarking with Importance Scoring (WIS). At each generation step, we estimate the importance of the token to generate, and prevent it from being impacted by watermarking if it is important for the semantic correctness of the output. We further propose three methods to predict importance scoring, including a perturbation-based method and two model-based methods. Empirical experiments show that our method can generate texts with better quality with comparable level of detection rate.

翻译：大语言模型（LLM）的强通用能力若被恶意用户无限制使用，将带来潜在伦理风险。词级水印技术通过使用前缀令牌作为种子的私有随机数生成器，改变令牌概率分布，在生成文本中嵌入水印。然而，这种水印算法在生成过程中会调整逻辑值，若其选择提升与输入相关性较低的令牌，则可能导致文本质量下降。本研究提出基于重要性评分的水印技术（WIS），以提升带水印语言模型生成文本的质量。在每个生成步骤中，我们评估待生成令牌的重要性，若该令牌对输出语义正确性至关重要，则避免其受到水印影响。此外，我们提出三种预测重要性评分的方法，包括基于扰动的方法和两种基于模型的方法。实证实验表明，本方法在保持检测率接近的前提下，可生成更高质量的文本。