Removing RLHF Protections in GPT-4 via Fine-Tuning.

Qiusi Zhan Richard Fang Rohan Bindu Akul Gupta Tatsunori Hashimoto Daniel Kang

Published in: CoRR (2023)

Keyphrases

fine tuning
viable alternative
fine tune
fine tuned
intellectual property
image processing
information technology
domain specific