Topic-based Watermarks for LLM-Generated Text

arXiv:2404.02138v1 Announce Type: cross
Abstract: Recent advancements of large language models (LLMs) have resulted in indistinguishable text outputs comparable to human-generated text. Watermarking algorithms are potential tools that offer a way to differentiate between LLM- and human-generated text by embedding detectable signatures within LLM-generated output. However, current watermarking schemes lack robustness against known attacks against watermarking algorithms. In addition, they are impractical considering an LLM generates tens of thousands of text outputs per day and the watermarking algorithm needs to …

abstract algorithms arxiv attacks cs.cl cs.cr cs.lg current embedding generated however human language language models large language large language models llm llms robustness text tools type watermarking watermarks