对齐的范围
Scopes of Alignment
AI总结：
本文提出超越通用价值观的AI对齐三个维度：能力、短暂性和受众，以扩展对齐范围并定位相关技术。
摘要：
关于AI对齐的许多研究焦点旨在将大型语言模型和其他基础模型与无上下文的通用价值观（如有用性、无害性和诚实性）对齐。前沿模型提供商也努力使其模型与这些价值观对齐。在本文中，我们论证了为何需要超越这种有限的概念，并提出了三个维度来做到这一点。对齐的第一个范围是能力：模型必须具备的知识、技能或行为，以便对其预期目的有用。对齐的第二个范围是短暂性：根据使用情境，可以是语义性的或情节性的。对齐的第三个范围是受众：可以是大众、公众、小群体或双人。在论文结尾，我们使用所提出的框架来定位一些超越现行对齐概念的技术和工作流程。
英文摘要：
Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align their models with these values. In this paper, we motivate why we need to move beyond such a limited conception and propose three dimensions for doing so. The first scope of alignment is competence: knowledge, skills, or behaviors the model must possess to be useful for its intended purpose. The second scope of alignment is transience: either semantic or episodic depending on the context of use. The third scope of alignment is audience: either mass, public, small-group, or dyadic. At the end of the paper, we use the proposed framework to position some technologies and workflows that go beyond prevailing notions of alignment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
