Provably Robust Multi-bit Watermarking for AI-generated Text via Error Correction Code

arXiv:2401.16820v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have been widely deployed for their remarkable capability to generate texts resembling human language. However, they could be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises ethical concerns. Watermarking is a key technique to mitigate the misuse of LLMs, which embeds a watermark (e.g., a bit string) into a text generated by a LLM. Consequently, this enables the detection of texts generated by …

arxiv code criminals cs.cr emails error ethical fake fake news generated human key language language models large llms phishing phishing emails text texts watermarking