1
ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration
无需访问模型内部，用闭式校准实现LLM文本水印，防篡改可溯源。
arXiv:2607.18445v1 Announce Type: cross Abstract: Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but exi…