Uncensor any LLM with abliteration

Reminds me of https://vgel.me/posts/representation-engineering/. There they were adding a control vector, w' = cvec + w, here they are "ablating" it, w' = w - dot(w,cvec)*cvec. There is an interesting field of learning how to "brain chip" LLMs into doing what you want.

There's so much work just like this coming out simultaneously.

Steering Vectors, Control Vectors, PyReft, PeFT improvements, Obliteration. It's a great time to be doing representation engineering.

There is some difference between fine-tuning with PyReft / PeFT, the approaches here are more on-the-fly. Like you can regenerate the control vectors from prompts in a few seconds.