Duwak: Dual Watermarks in Large Language Models

arXiv:2403.13000v1 Announce Type: new
Abstract: As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in embedding single human-imperceptible and machine-detectable patterns without significantly affecting generated text quality and semantics. However, the efficiency in detecting watermarks, i.e., the minimum number of tokens required to assert detection with significance and robustness against post-editing, is still debatable. In this …

abstract applications arxiv audit cs.ai cs.cl cs.cr cs.lg embedding generated human language language models large language large language models llm machine patterns quality semantics tasks text text generation type watermark watermarks