Yavuz Bakman

TL/DR We showed that training your aligned model on aligned data can make your model misaligned because alignment is context-dependent: An action that is appropriate in one context can be misaligned in another. We showed that training LLMs on samples containing contextually appropriate actions can cause those actions to jump...

Models that appear aligned under black-box evaluation may conceal substantial latent misalignment beneath their observable behavior. Let's say you downloaded a language model from Huggingface. You do all the blackbox evaluation for the safety/alignment, and you are convinced that the model is safe/aligned. But how badly can things go after...