Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

8 February 2024

Papers citing "Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs"

5 / 5 papers shown

Title
Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning Li An Yujian Liu Y. Liu Yang Zhang Yuheng Bu Shiyu Chang AAML 70 0 0 09 Apr 2025
Watermarking Makes Language Models Radioactive Tom Sander Pierre Fernandez Alain Durmus Matthijs Douze Teddy Furon WaLM 29 11 0 22 Feb 2024
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused? Hangfan Zhang Zhimeng Guo Huaisheng Zhu Bochuan Cao Lu Lin Jinyuan Jia Jinghui Chen Di Wu 70 23 0 02 Oct 2023
Robust Multi-bit Natural Language Watermarking through Invariant Features Kiyoon Yoo Wonhyuk Ahn Jiho Jang Nojun Kwak WaLM 136 76 0 03 May 2023
Permute-and-Flip: A new mechanism for differentially private selection Ryan McKenna Daniel Sheldon 105 47 0 23 Oct 2020