Article Details
Retrieved on: 2025-01-03 23:21:45
Tags for this article:
Click the tags to see associated articles and topics
Summary
The article discusses a novel jailbreak method, Bad Likert Judge, leveraging large language models’ abilities using Likert scales to generate harmful content. This connects to psychometrics, deep learning, and NLP through survey methodologies and prompt engineering.
Article found on: www.scworld.com
This article is found inside other hiswai user's workspaces. To start your own collection, sign up for free.
Sign UpAlready have an account? Log in here