Year: 2024
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Anwar, Usman, Saparov, Abulhair, Rando Ramirez, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Lubana, Ekdeep Singh, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L., Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi Chenyu, Zhong, Ruiqi, Ó hÉigeartaigh, Seán, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Petrov, Aleksandar, Schroeder de Witt, Christian, Motwani, Sumeet Ramesh, Bengio, Yoshua, Chen, Danqi, Torr, Philip H.S., Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob Nicolaus, Tramèr, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6947695150