Beast code in Giters

RobustNLP's repositories

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

Language:PythonMIT614 100

A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.

Language:PythonMIT59 50

A toolkit for testing machine translation [ICSE'20, '21, ESEC/FSE'20]

Language:PythonMIT33 3 2

A toolkit for testing and improving named entity recognition [ESEC/FSE'23]

Language:PythonMIT11 20

A toolkit for testing image captioning [ISSTA'22, '23]

Language:PythonMIT7 2 2