Aligned Data Can Induce Severe Misalignment via Context Confusion
TL/DRWe 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 to other contexts where they are harmful. We called this phenomenon context confusion and provided model organisms (datasets creating context confusion), showed its existence...
Read full article →