A watermark for chatbots that can detect text written by AI
For example, since OpenAI’s ChatGPT chatbot was launched in November, students have started using it to cheat by writing essays for them. CNET news site used ChatGPT to write articles, just for release corrections Between accusations Plagiarism. But there is a promising way to detect AI text: by embedding hidden patterns that allow us to identify AI-generated text into these systems before they are even released.
In studies, these watermarks have shown that they can almost certainly identify AI-generated text. One, developed by a team at the University of Maryland, can detect text generated by Meta’s open source language model, OPT-6.7B, using the detection algorithm they built. The job is described in a paper that hasn’t been peer-reviewed yet, and code will be available Free around February 15th.
AI language models work by predicting and generating words one by one. After each word, the fuzzy marking algorithm randomly divides the language model’s vocabulary into words from the “green list” and “red list”, and then prompts the language model to select the words from the green list. .
The more greenlisted words in a paragraph, the more likely it is that the text is machine generated. Text written by one person tends to contain more random mixed words. For example, for the word “beautiful”, the watermarking algorithm can classify the word “flower” as green and “orchid” as red. Tom Goldstein, an assistant professor at the University of Maryland who was involved in the study, explains: An AI model with a watermarking algorithm would be more likely to use the word “flower” rather than “orchid”.