On the Learnability of Watermarks for Language Models
Collection
Paper: https://arxiv.org/abs/2312.04469 (ICLR 2024), GitHub: https://github.com/chenchenygu/watermark-learnability
•
50 items
•
Updated
Logits-based watermark distilled Llama 2 7B using the Aar watermarking strategy in the paper On the Learnability of Watermarks for Language Models.
The following hyperparameters were used during training: