Nowadays, Ethic AI is one the trending tech in AI domain.
So they try to block every jailbreaks to secure the AI industry especially LLMs.
But these all methods have their own weak point. Because the knowledge has already placed in LLM. Then how can I delete that data from LLM?
Please guide me which frameworks can do that?
How about machine unlearning? But I don’t know anything about machine unlearning.
Give me guide step by step.
2 Likes
How about abliteration?
First,you must have the enough knowledge of learning process of LLMs then you can do that .
2 Likes
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.