Computer ScienceNature
Scalable watermarking for identifying large language model outputs
S. Dathathri, A. See, et al.
Discover how Sumanth Dathathri and colleagues at Google DeepMind have tackled the challenges of identifying AI-generated content through their innovative SynthID-Text watermarking scheme. This groundbreaking research ensures high-quality synthetic text generation while maintaining detection accuracy and speed.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Medicine and Health
A scoping review of large language model based approaches for information extraction from radiology reports
D. Reichenpfader, H. Müller, et al.
Linguistics and Languages
Applying large language models for automated essay scoring for non-native Japanese
W. Li and H. Liu
Psychology
Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation
E. C. Stade, S. W. Stirman, et al.
Chemistry
TransPolymer: a Transformer-based language model for polymer property predictions
C. Xu, Y. Wang, et al.
