做 LLM 内容溯源或版权保护的团队终于有了一个既不影响生成质量、又能抗稀释的实用方案，建议关注其蒸馏检测能力。
TextSeal 是一种新型大语言模型水印方案，基于 Gumbel-max 采样并引入双密钥生成、熵加权评分和多区域定位，显著提升检测能力。它不增加推理开销，支持投机解码和多 token 预测等优化，在检测强度上严格优于 SynthID-text。即使在人类与 AI 混合文本中也能保持高置信度本地化检测，且理论上无失真。多语言人工评估（6000 次 A/B 比较，5 种语言）显示无感知质量差异。此外，水印信号可通过模型蒸馏传递，实现未经授权使用的检测。
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
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.