Search Results for author: William Schulze

Found 1 papers, 1 papers with code

I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models

1 code implementation6 Jun 2023 Max Reuter, William Schulze

With this machine-labeled data, we train a prompt classifier to predict whether ChatGPT will refuse a given question, without seeing ChatGPT's response.

Cannot find the paper you are looking for? You can Submit a new open access paper.