An Entropy-based Text Watermarking Detection Method

arXiv:2403.13485v1 Announce Type: new
Abstract: Currently, text watermarking algorithms for large language models (LLMs) can embed hidden features to texts generated by LLMs to facilitate subsequent detection, thus alleviating the problem of misuse of LLMs. Although the current text watermarking algorithms perform well in most high-entropy scenarios, its performance in low-entropy scenarios still needs to be improved. In this work, we proposed that the influence of token entropy should be fully considered in the watermark detection process, that is, the …

abstract algorithms arxiv cs.cl current detection embed entropy features generated hidden language language models large language large language models llms low misuse performance text type watermarking