| 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 | 439 | 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 | 119 | 2024 |
| Reward model ensembles help mitigate overoptimization T Coste, U Anwar, R Kirk, D Krueger arXiv preprint arXiv:2310.02743, 2023 | 81 | 2023 |
| Inverse Constrained Reinforcement Learning S Malik, U Anwar, A Aghasi, A Ahmed International Conference on Machine Learning, 7390-7399, 2021 | 70* | 2021 |
| Bayesian methods for constraint inference in reinforcement learning D Papadimitriou, U Anwar, DS Brown | 25* | 2022 |
| Learning to solve differential equations across initial conditions S Malik, U Anwar, A Ahmed, A Aghasi arXiv preprint arXiv:2003.12159, 2020 | 10 | 2020 |
| Foundational challenges in assuring alignment and safety of large language models. arXiv U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ... preprint, 2024 | 8 | 2024 |
| IDs for AI Systems A Chan, N Kolt, P Wills, U Anwar, CS de Witt, N Rajkumar, L Hammond, ... arXiv preprint arXiv:2406.12137, 2024 | 4 | 2024 |
| Adversarial robustness of in-context learning in transformers for linear regression U Anwar, J Von Oswald, L Kirsch, D Krueger, S Frei arXiv preprint arXiv:2411.05189, 2024 | 3 | 2024 |
| Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks M Brumley, J Kwon, D Krueger, D Krasheninnikov, U Anwar arXiv preprint arXiv:2411.07213, 2024 | 1 | 2024 |
| Domain Generalization for Robust Model-Based Offline Reinforcement Learning A Clark, SA Siddiqui, R Kirk, U Anwar, S Chung, D Krueger arXiv preprint arXiv:2211.14827, 2022 | 1 | 2022 |
| The Reality of AI and Biorisk A Peppin, A Reuel, S Casper, E Jones, A Strait, U Anwar, A Agrawal, ... arXiv preprint arXiv:2412.01946, 2024 | | 2024 |
| Learning to Forget using Hypernetworks JML Rangel, S Schoepf, J Foster, D Krueger, U Anwar arXiv preprint arXiv:2412.00761, 2024 | | 2024 |
| Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games U Anwar, A Pandian, J Wan, D Krueger, J Foerster arXiv preprint arXiv:2411.04976, 2024 | | 2024 |