Towards Codable Watermarking for Injecting Multi-bits Information to LLMs

arXiv:2307.15992v3 Announce Type: replace
Abstract: As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user …

arxiv cs.cl information llms type watermarking