Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a watermarking framework for proprietary language models. The watermark can be embedded with negligible impact on text quality, and can be detected using an efficient open-source algorithm without access to the language model API or parameters. The watermark works by selecting a randomized set of "green" tokens before a word is generated, and then softly promoting use of green tokens during sampling. We propose a statistical test for detecting the watermark with interpretable p-values, and derive an information-theoretic framework for analyzing the sensitivity of the watermark. We test the watermark using a multi-billion parameter model from the Open Pretrained Transformer (OPT) family, and discuss robustness and security.

翻译：大型语言模型的潜在危害可以通过对模型输出添加水印来缓解，即向生成的文本中嵌入人类不可见但可通过短序列令牌进行算法检测的信号。我们针对专有语言模型提出了一种水印框架。该水印可在对文本质量影响极小的前提下嵌入，并且能够通过高效的开源算法检测，无需访问语言模型的API或参数。其工作原理是在生成单词前随机选择一组“绿色”令牌，并在采样过程中温和地促进使用这些绿色令牌。我们提出了一种统计检验方法，通过可解释的p值检测水印，并推导出分析水印敏感性的信息论框架。我们使用来自开放预训练Transformer（OPT）系列的数十亿参数模型对水印进行了测试，并讨论了其鲁棒性与安全性。