研究人员开发了一种名为SSG（按组排序后拆分）的新方法，以提高大型语言模型（LLM）水印的有效性。现有的水印技术，如KGW方案，在代码和数学推理等低熵内容方面存在困难。SSG通过将词汇表划分为对数平衡的子集来解决这个问题，从而提高了水印的可检测性。实验表明，SSG在代码生成和数学推理任务上是有效的。 AI
影响 提高了LLM内容的追溯性，尤其是在代码和数学输出方面。
排序理由 介绍LLM水印新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.22438v1 Announce Type: cross Abstract: Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, effici…
Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and effectiveness in natural language genera…