On the Reliability of Watermarks for Large Language Models

arXiv:2306.04634v4 Announce Type: replace-cross
Abstract: As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the detection and documentation of LLM-generated text. Yet a crucial question remains: How reliable is watermarking in realistic settings in the wild? There, watermarked text may be modified to suit a user's needs, or entirely rewritten to avoid detection. We study …

abstract arxiv become bots cs.cl cs.cr cs.lg detection documentation enabling flood generated internet language language models large language large language models llm llms machine media question reliability simple social social media spam strategy text type watermarking watermarks