Introducing SynthID Text

Do you find it difficult to tell if text was written by a human or generated by AI? Being able to identify AI-generated content is essential to promoting trust in information, and helping to address problems such as misattribution and misinformation. Today, Google DeepMind and Hugging Face are excited to launch SynthID Text in Transformers v4.46.0, releasing later today. This technology allows you to apply watermarks to AI-generated text using a logits processor for generation tasks, and detect those watermarks with a classifier.

Check out the SynthID Text paper in Nature for the complete technical details of this algorithm, and Google’s Responsible GenAI Toolkit for more on how to apply SynthID Text in your products.

How it works

The primary goal of SynthID Text is to encode a watermark into AI-generated text in a way that helps you determine if text was generated from your LLM without affecting how the underlying LLM works or negatively impacting generation quality. Google DeepMind has developed a watermarking technique that uses a pseudo-random function, called a g-function, to augment the generation process of any LLM such that the watermark is imperceptible to humans but is visible to a trained model. This has been implemented as a generation utility that is compatible with any LLM without modification using the model.generate() API, along with an end-to-end example of how to train detectors to recognize watermarked text. Check out the research paper that has more complete details about the SynthID Text algorithm.

Configuring a watermark

Watermarks are configured using a dataclass that parameterizes the g-function and how it is applied in the tournament sampling process. Each model you use should have its own watermarking configuration that should be stored securely and privately, otherwise your watermark may be replicable by others.

You must define two parameters in every watermarking configuration: