| 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 | 478 | 2023 |
| On the Utility of Learning About Humans for Human-AI Coordination M Carroll, R Shah, MK Ho, T Griffiths, S Seshia, P Abbeel, A Dragan Advances in Neural Information Processing Systems, 2019, 5174-5185, 2019 | 471 | 2019 |
| 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 | 121* | 2023 |
| Estimating and Penalizing Induced Preference Shifts in Recommender Systems M Carroll, A Dragan, S Russell, D Hadfield-Menell International Conference on Machine Learning, 2022 (Spotlight), 2686-2708, 2022 | 77* | 2022 |
| Characterizing Manipulation from AI Systems M Carroll*, A Chan*, H Ashton, D Krueger EEAMO 2023, 2023 | 63 | 2023 |
| Engagement, user satisfaction, and the amplification of divisive content on social media S Milli, M Carroll, Y Wang, S Pandey, S Zhao, AD Dragan arXiv preprint arXiv:2305.16941, 2023 | 52* | 2023 |
| Uni[MASK]: Unified inference in sequential decision problems M Carroll, O Paradise, J Lin, R Georgescu, M Sun, D Bignell, S Milani, ... NeurIPS 2022 (Oral), 2022 | 41* | 2022 |
| Evaluating the Robustness of Collaborative Agents P Knott, M Carroll, S Devlin, K Ciosek, K Hofmann, AD Dragan, R Shah AAMAS 2021 (Extended Abstract), 2021 | 32 | 2021 |
| Beyond preferences in ai alignment T Zhi-Xuan, M Carroll, M Franklin, H Ashton Philosophical Studies, 1-51, 2024 | 16 | 2024 |
| Ai alignment with changing and influenceable reward functions M Carroll, D Foote, A Siththaranjan, S Russell, A Dragan arXiv preprint arXiv:2405.17713, 2024 | 16 | 2024 |
| Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration M Yang, M Carroll, A Dragan NeurIPS 2022 Human in the Loop Learning (HiLL) Workshop, 2022 | 10 | 2022 |
| Humanity's Last Exam L Phan, A Gatti, Z Han, N Li, J Hu, H Zhang, S Shi, M Choi, A Agrawal, ... arXiv preprint arXiv:2501.14249, 2025 | 8 | 2025 |
| On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback M Williams*, M Carroll*, A Narang, C Weisser, B Murphy, A Dragan arXiv preprint arXiv:2411.02306, 2024 | 7* | 2024 |
| Who Needs to Know? Minimal Knowledge for Optimal Coordination N Lauffer, A Shah, M Carroll, MD Dennis, S Russell International Conference on Machine Learning 2023, 18599-18613, 2023 | 5 | 2023 |
| Time-Efficient Reward Learning via Visually Assisted Cluster Ranking D Zhang, M Carroll, A Bobu, A Dragan NeurIPS 2022 Human in the Loop Learning (HiLL) Workshop, 2022 | 5 | 2022 |
| Overview of current AI alignment approaches M Carroll | 3 | 2018 |
Anca D DraganAssistant Professor at UC Berkeley // Director, AI Safety and Alignment, Google DeepMindPatvirtintas el. paštas berkeley.edu
