DiveR-CT: Diversity-enhanced Red Teaming with Relaxing Constraints

[PDF] arxiv.org

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

H Wang, Y Yue, R Lu, J Shi, A Zhao, S Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated great potential as generalist assistants,
showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs …
相关文章 所有 2 个版本