Scalable watermarking for identifying large language model outputs.

ABSTRACT: Large language models (LLMs) have enabled the generation of high-quality synthetic text, often indistinguishable from human-written content, at a scale that can markedly affect the nature of the information ecosystem^1-3. Watermarking can help identify synthetic text and limit accidental or deliberate misuse⁴, but has not been adopted in production systems owing to stringent quality, detectability and computational efficiency requirements. Here we describe SynthID-Text, a production-ready text watermarking scheme that preserves text quality and enables high detection accuracy, with minimal latency overhead. SynthID-Text does not affect LLM training and modifies only the sampling procedure; watermark detection is computationally efficient, without using the underlying L

SUBMITTER: Dathathri S 

PROVIDER: S-EPMC11499265 | biostudies-literature | 2024 Oct

REPOSITORIES: biostudies-literature