With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability and their impact on the quality of the generated text. This paper introduces a systematic approach to this trade-off in terms of a multi-objective optimization problem. For a large class of robust, efficient watermarks, the associated Pareto optimal solutions are identified and shown to outperform the currently default watermark.

翻译：随着大语言模型（LLMs）的兴起及其潜在滥用问题的担忧，针对生成式LLMs的水印技术近期引起了广泛关注。这类水印的关键挑战在于其可识别性与生成文本质量之间的权衡。本文从多目标优化问题的角度，系统性地探讨了这一权衡关系。针对一类具有鲁棒性和高效性的水印方案，我们确定了相应的帕累托最优解，并证明其性能优于当前默认的水印算法。