We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity, along with entropy-weighted scoring and multi-region localization for improved detection. It supports serving optimizations such as speculative decoding and multi-token prediction, and does not add any inference overhead. TextSeal strictly dominates baselines like SynthID-text in detection strength and is robust to dilution, maintaining confident localized detection even in heavily mixed human/AI documents. The scheme is theoretically distortion-free, and evaluation across reasoning benchmarks confirms that it preserves downstream performance; while a multilingual human evaluation (6000 A/B comparisons, 5 languages) shows no perceptible quality difference. Beyond its use for provenance detection, TextSeal is also ``radioactive'': its watermark signal transfers through model distillation, enabling detection of unauthorized use.

翻译：本文提出TextSeal——一种面向大语言模型的先进水印技术。该方案基于Gumbel-max采样框架，通过引入双密钥生成机制恢复输出多样性，并采用熵加权评分与多区域局部化方法提升检测效能。TextSeal支持推测解码与多词元预测等服务优化策略，且不引入任何推理开销。在检测强度上，该方案严格优于SynthID-text等基线方法，并具备抗稀释鲁棒性——即便在高度混合的人机协作文档中仍能保持可靠的局部化检测。理论分析表明该方案具有无损特性，基于推理基准的评估证实其不会影响下游任务性能；跨语言人工评估（含6000次A/B对比，覆盖5种语言）显示质量无感知差异。除溯源检测外，TextSeal还具有“放射性”特质：其水印信号可通过模型蒸馏传播，从而实现未授权使用的检测。