Zobrazeno 1 - 10
of 607
pro vyhledávání: '"DERAKHSHAN, Ali"'
Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational model tra
Externí odkaz:
http://arxiv.org/abs/2311.00172
Publikováno v:
In System October 2024 125
Publikováno v:
In Learning and Motivation August 2024 87
Publikováno v:
In Computers in Human Behavior January 2025 162
Autor:
Garakani, Amir Akbari, Derakhshan, Ali
Publikováno v:
In Geothermics November 2024 123
Publikováno v:
In Surface & Coatings Technology 30 July 2024 488
Autor:
Khazaie, Saeed, Derakhshan, Ali
Publikováno v:
In English for Specific Purposes July 2024 75:15-36
Autor:
Derakhshan, Ali, Fathi, Jalil
Publikováno v:
In System July 2024 123