AI RESEARCH
WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking
arXiv CS.CL
•
ArXi:2512.00837v3 Announce Type: replace Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Existing approaches typically embed signals by manipulating token generation probabilities.