作者
Jiaming Ji,Tianyi Qiu,Boyuan Chen,Jiayi Zhou,Borong Zhang,Dawei Hong,Hantao Lou,K. Wang,Yawen Duan,Zhonghao He,Lukas Vierling,Zhaowei Zhang,F. R. Zeng,Juntao Dai,Xuehai Pan,Hua Xu,Aidan O’Gara,Kwan Yee Ng,Brian Tse,Jie Fu
摘要
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 the distribution shift. Specifically, we survey traditional preference modeling methods and reinforcement learning from human feedback and further discuss potential frameworks to reach scalable oversight for tasks where effective human oversight is hard to obtain. Within learning under distribution shift, we also cover data distribution interventions such as adversarial training that helps expand the distribution of training data and algorithmic interventions to combat goal misgeneralization. On backward alignment, we discuss assurance techniques and governance practices. Specifically, we survey assurance methods of AI systems throughout their lifecycle, covering safety evaluation, interpretability, and human value compliance. We discuss current and prospective governance practices adopted by governments, industry actors, and other third parties, aimed at managing existing and future AI risks. This survey aims to provide a comprehensive yet beginner-friendly review of alignment research topics. Based on this, we also release and continually update the website www.alignmentsurvey.com which features tutorials, collections of papers, blog posts, and other resources.