نسخة أولية وصول مفتوح
Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment
Modern AI models are aligned through post-training to adapt them to downstream tasks. Recent work shows that fine-tuning language models on narrow tasks can induce emergent misalignment (EM), causing broadly harmful behaviors beyond the training task. However, EM has been studied almost entirely in text-only tasks, lea …