Exploring Safety Generalization Challenges of Large Language Models via Code

arXiv:2403.07865v1 Announce Type: cross
Abstract: The rapid advancement of Large Language Models (LLMs) has brought about remarkable capabilities in natural language processing but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods primarily focus on natural languages, which may not generalize to other domains. This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs, presenting a novel environment for testing the …

advancement arxiv capabilities challenges code cs.ai cs.cl cs.cr cs.lg cs.se feedback fine-tuning focus human language language models large llms natural natural language natural language processing rapid safety strategies