Year: 2024
Type: article
Abstract: This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose 200+ concrete research questions.
Authors: Anwar, U, Saparov, A, Rando, J, Paleka, D, Turpin, M, Hase, P, Lubana, ES, Jenner, E, Casper, S, Sourbut, O, Edelman, BL, Zhang, Z, Günther, M, Korinek, A, Hernandez-Orallo, J, Hammond, L, Bigelow, E, Pan, A, Langosco, L, Korbak, T, Zhang, H, Zhong, R, Héigeartaigh, S, Recchia, G, Corsi, G, Chan, A, Anderljung, M, Edwards, L, Petrov, A, Schroeder de Witt, C, Motwani, SR, Bengio, Y, Chen, D, Torr, PHS, Albanie, S, Maharaj, T, Foerster, J, Tramer, F, He, H, Kasirzade, A, Choi, Y, Krueger, D
Institutions: University of Cambridge, New York University, ETH Zurich, University of North Carolina at Chapel Hill, University of Michigan, University of California, Berkeley, Massachusetts Institute of Technology, University of Oxford, Harvard University, Peking University, Ludwig-Maximilians-Universität München, University of Virginia, Universitat Politècnica de València, Stanford University, Newcastle University, Mila - Quebec Artificial Intelligence Institute, Université de Montréal, Princeton University, University of Toronto, University of Washington, Allen Institute for Artificial Intelligence
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225217078