AI Alignment: A Comprehensive Survey
It addresses the critical issue of AI misalignment risks for researchers and practitioners, but is incremental as it synthesizes existing work rather than proposing new methods.
This survey tackles the problem of aligning AI systems with human intentions and values by introducing the RICE principles (Robustness, Interpretability, Controllability, Ethicality) and decomposing alignment into forward and backward components, providing a comprehensive overview of current research and resources.
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.