Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Abstract

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

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.

Publication date
Author(s)
Bibliographic reference (EN)

Anwar, U., Saparov, A., Rando, J., Paleka, D., Turpin, M., Hase, P., Lubana, E. S., Jenner, E., Casper, S., Sourbut, O., Edelman, B. L., Zhang, Z., Günther, M., Korinek, A., Hernandez-Orallo, J., Hammond, L., Bigelow, E., Pan, A., Langosco, L., Korbak, T., Ó hÉigeartaigh, S., Recchia, G., Corsi, G., Chan, A., Anderljung, M., Edwards, L., Petrov, A., Schroeder de Witt, C., Motwani, S. R., Bengio, Y., & Others. (2024, September 2). Foundational challenges in assuring alignment and safety of large language models [Poster summary]. Transactions on Machine Learning Research.

Partner(s)
  • Université de Montréal
  • Mila

Stay up to date with the latest news!

Receive updates from the community, upcoming events, and research opportunities.