Safety Pretraining: Toward the Next Generation of Safe AI

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during pretraining, they are hard to remove. In this work, we present a data-centric pretraining framework that builds safety into the model from the start. Our framework consists of four key steps: (i) Safety Filtering: building a safety classifier to classify webdata into safe and unsafe categories; (ii) Safety Rephrasing: we recontextualize unsafe webdata into safer narratives; (iii) Native Refusal: we synthetically generate pretraining datasets that actively teach models to refuse on unsafe content and the moral reasoning behind it, and (iv) Harmfulness-Tag annotated pretraining: we flag unsafe content during pretraining using a special token, and use it to steer models away from unsafe generations at inference-time. Our safety-pretrained models reduce attack success rates from 38. 8% to 8. 4% on standard LLM safety benchmarks with no performance degradation on general tasks.

Authors

• Pratyush Maini
• Sachin Goyal
• Dylan Sam Carnegie Mellon University
• Alexander Robey
• Yash Savani
• Yiding Jiang
• Andy Zou
• Matt Fredrikson
• Zachary Lipton
• Zico Kolter

Keywords

No keywords are indexed for this paper.