A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
Morphmark: Flexible adaptive watermarking for large language models.arXiv preprint arXiv:2505.11541
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
TextSeal provides a localized, distortion-free LLM watermark that outperforms baselines in detection strength, remains effective in mixed human-AI text, preserves model performance, and transfers through distillation for provenance tracking.
XMark improves multi-bit watermarking for LLM text by using a less distorted logit distribution in encoding and a tailored decoder for reliable recovery even with limited tokens.
citing papers explorer
-
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
-
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
TextSeal provides a localized, distortion-free LLM watermark that outperforms baselines in detection strength, remains effective in mixed human-AI text, preserves model performance, and transfers through distillation for provenance tracking.
-
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
XMark improves multi-bit watermarking for LLM text by using a less distorted logit distribution in encoding and a tailored decoder for reliable recovery even with limited tokens.