Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM watermark), is a standout solution for safeguarding machine-generated texts due to its notable detectability. However, GM watermark encounters a major challenge with generation diversity, always yielding identical outputs for the same prompt, negatively impacting generation diversity and user experience. To overcome this limitation, we propose a new type of GM watermark, the Logits-Addition watermark, and its three variants, specifically designed to enhance diversity. Among these, the GumbelSoft watermark (a softmax variant of the Logits-Addition watermark) demonstrates superior performance in high diversity settings, with its AUROC score outperforming those of the two alternative variants by 0.1 to 0.3 and surpassing other decoding-based watermarking methods by a minimum of 0.1.

翻译：大型语言模型能够出色地生成类似人类的文本，但也引发了对虚假新闻和学术不端行为滥用风险的担忧。基于解码的水印方法，特别是基于GumbelMax技巧的水印（GM水印），因其显著的可检测性，成为保护机器生成文本的突出解决方案。然而，GM水印在生成多样性方面面临重大挑战，总是对同一提示生成相同输出，对生成多样性和用户体验产生负面影响。为克服这一局限，我们提出了一种新型GM水印——对数加法水印及其三种变体，专门设计用于增强多样性。其中，GumbelSoft水印（对数加法水印的softmax变体）在高多样性场景下表现出优越性能，其AUROC评分比两种替代变体高0.1至0.3，且比其他基于解码的水印方法至少高出0.1。