✳flâneur — a map of the web's best reading

Scalable watermarking for identifying large language model outputs | Nature

nature.com · 243 words · saved by 1 readers

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement Nature volume 634, pages 818–823 (2024)Cite this article 5313 Accesses 1 Citations 819 Altmetric Metrics details 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 ecosystem1,2,3. 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

Download PDF Subjects Computer science Information technology 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 , 2 , 3 . Watermarking can help identify synthetic text and limit accidental or deliberate misuse 4 , 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 t

Explore this link on the map →

related reading