← all papers · overview

Can Watermarked Llms Be Identified By Users Via Crafted Prompts?

Abstract

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigation into the imperceptibility of watermarking techniques in LLM services. This is crucial as LLM providers

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).