Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

arXiv:2309.07875v3 Announce Type: replace
Abstract: Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily generate harmful content. In this paper, we raise concerns over the safety of models that only emphasize helpfulness, not harmlessness, in their instruction-tuning. We show that several popular instruction-tuned models are highly unsafe. Moreover, we show that adding just …

abstract arxiv become cs.cl generate however language language models large language large language models llamas safety tasks them training type will