Foundational Challenges in Assuring Alignment and Safety of Large Language Models

作者：Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, Jose Hernandez-Orallo, Lewis Hammond, Eric Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Aleksandar Petrov, Christian Schroeder de Witt · 单位：Published in Transactions on Machine Learning Research (09/2024, University of Cambridge New York University ETH Zurich UNC Chapel Hill, University of Michigian University of California, Berkeley Massachusetts Institute of Technology, University of Oxford Harvard University Peking University LMU Munich, Stanford University Modulo Research Center for the Governance of AI, Newcastle University Mila - Quebec AI Institute, Université de Montréal Princeton University · 会议/期刊：arXiv preprint · 方向：泛化能力 / 安全可控智能体 · 发布日期：2024-04-15