Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
AlphaUncommon

RobustNLP/CipherChat

A framework to evaluate the generalization capability of safety alignment for LLMs

Owner
RobustNLP (organization)
Stars
Stars: 629
Forks
Forks: 66
Language
Python
License
MIT
Created
2023
Topics
alignmentjailbreaklarge-language-modelsllmsecuritychatgptgpt-4-0613
Tier
Alpha (250 to 699 ★) What this tier means
View on GitHub

Nearby in Python

All Python repos