| Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... arXiv preprint arXiv:2307.15217, 2023 | 875 | 2023 |
| Foundational Challenges in Assuring Alignment and Safety of Large Language Models U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ... arXiv preprint arXiv:2404.09932, 2024 | 296 | 2024 |
| Harms from Increasingly Agentic Algorithmic Systems A Chan, R Salganik, A Markelius, C Pang, N Rajkumar, D Krasheninnikov, ... Proceedings of the 2023 ACM Conference on Fairness, Accountability, and …, 2023 | 264* | 2023 |
| Goal Misgeneralization in Deep Reinforcement Learning L Langosco, J Koch, L Sharkey, J Pfau, L Orseau, D Krueger ICML 2022, 9, 2022 | 213 | 2022 |
| Unifying Grokking and Double Descent X Davies, L Langosco, D Krueger ML Safety Workshop Neurips 2022, 2023 | 55 | 2023 |
| Neural Variational Gradient Descent L Langosco di Langosco, V Fortuin, H Strathmann ICML Workshop on Uncertainty & Robustness in Deep Learning, 2021 | 28* | 2021 |
| Detecting Backdoors with Meta-Models L Langosco, N Alex, W Baker, D Quarel, H Bradley, D Krueger NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and …, 2023 | 8 | 2023 |
| Training Equilibria in Reinforcement Learning L Langosco, D Krueger, A Gleave Deep Reinforcement Learning Workshop NeurIPS 2022, 2022 | 1* | 2022 |
David Scott KruegerAssistant Professor, University of Montreal, MilaVerified email at cam.ac.uk
