With the rapid growth of Large Language Models (LLMs), criticism of their societal impact has also grown. Work in Responsible AI (RAI) has focused on the development of AI systems aimed at reducing harm. Responding to RAI's criticisms and the need to bring the wisdom traditions into HCI, we apply Conwill et al.'s Virtue-Guided Technology Design method to LLMs. We cataloged new ethical design patterns for LLMs and evaluated them through interviews with technologists. Participants valued that the patterns provided more accuracy and robustness, better safety, new research opportunities, increased access and control, and reduced waste. Their concerns were that the patterns could be vulnerable to jailbreaking, were generalizing models too widely, and had potential implementation issues. Overall, participants reacted positively while also acknowledging the tradeoffs involved in ethical LLM design.

翻译：随着大语言模型（LLMs）的快速发展，对其社会影响的批评也日益增多。负责任人工智能（RAI）领域的研究致力于开发旨在减少危害的AI系统。为回应RAI的批评，并将传统智慧引入人机交互领域，我们将Conwill等人提出的美德导向技术设计方法应用于大语言模型。我们系统梳理了适用于大语言模型的新型伦理设计模式，并通过与技术专家的访谈对其进行了评估。参与者认为这些模式具有以下价值：提供更高的准确性与鲁棒性、更好的安全性、新的研究机遇、更强的可访问性与可控性，并能减少资源浪费。他们担忧的问题包括：这些模式可能易受越狱攻击、模型泛化范围过宽，以及存在潜在的实施难题。总体而言，参与者反应积极，同时也认识到伦理化大语言模型设计所涉及的权衡取舍。