NVIDIA NeMo Guardrails Documentation, NVIDIA, 2023 (NVIDIA) - Provides an open-source framework for building configurable safety guardrails for LLM applications.
A Survey of Large Language Models, Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, Ji-Rong Wen, 2023arXiv preprint arXiv:2303.18223DOI: 10.48550/arXiv.2303.18223 - Includes a comprehensive section on LLM safety and alignment techniques, contextualizing external guardrails within a broader safety framework.
Microsoft Responsible AI Standard v2, Microsoft, 2022 (Microsoft) - Outlines principles and practices for responsible AI development, providing context for the importance of safety mechanisms like guardrails in deployed systems.