Defending LLM watermarking against spoofing attacks with contrastive representation learningApr 9, 2025·Li An,Yujian Liu,Yepeng Liu,Yang Zhang,Yuheng Bu,Shiyu Chang· 0 min read PDF CiteTypeConference paperPublicationCOLM 2025Last updated on Apr 9, 2025 AuthorsLi AnPhD Student ← A Reinforcement Learning Framework for Robust and Secure LLM Watermarking Oct 23, 2025Towards Chapter-to-Chapter Context-Aware Literary Translation via Large Language Models Jul 12, 2024 →
