#natural language process...
Jun 2026
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
Experimental results show that dual-embedding watermarking can offer state-of-the-art robustness, particularly against translation, while incurring relatively low computational overhead compared with other semantic schemes.
Jonas Schäfer, Cezary Pilaszewicz, Gerhard Wunder
· arXiv.org · 0 citations