Foundational Challenges in Assuring Alignment and Safety of Large Language Models
/ Authors
Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, E. Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut
and 28 more authors
Benjamin L. Edelman, Zhaowei Zhang, Mario Gunther, Anton Korinek, J. Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, L. Langosco, Tomasz Korbak, H. Zhang, Ruiqi Zhong, Se'an 'O h'Eigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Y. Bengio, Danqi Chen, Samuel Albanie, Tegan Maharaj, J. Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger
/ 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.
Journal: ArXiv