William S. Isaac
William S. Isaac
Staff Research Scientist, Deepmind Ethics and Society
Verified email at - Homepage
Cited by
Cited by
Ethical and social risks of harm from language models
L Weidinger, J Mellor, M Rauh, C Griffin, J Uesato, PS Huang, M Cheng, ...
arXiv preprint arXiv:2112.04359, 2021
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
JW Rae, S Borgeaud, T Cai, K Millican, J Hoffmann, F Song, J Aslanides, ...
arXiv preprint arXiv:2112.11446, 2021
To predict and serve?
K Lum, WS Isaac
Significance 13 (5), 14-19, 2016
Gemini: a family of highly capable multimodal models
G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ...
arXiv preprint arXiv:2312.11805, 2023
Decolonial AI: Decolonial theory as sociotechnical foresight in artificial intelligence
S Mohamed, MT Png, W Isaac
Philosophy & Technology 33, 659-684, 2020
Improving alignment of dialogue agents via targeted human judgements
A Glaese, N McAleese, M Trębacz, J Aslanides, V Firoiu, T Ewalds, ...
arXiv preprint arXiv:2209.14375, 2022
Power to the People? Opportunities and Challenges for Participatory AI
A Birhane, W Isaac, V Prabhakaran, M Díaz, MC Elish, I Gabriel, ...
Equity and Access in Algorithms, Mechanisms, and Optimization, 1-8, 2022
A causal Bayesian networks viewpoint on fairness
S Chiappa, WS Isaac
Privacy and Identity Management. Fairness, Accountability, and Transparency …, 2019
Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics
D Martin Jr, V Prabhakaran, J Kuhlberg, A Smart, WS Isaac
arXiv preprint arXiv:2005.07572, 2020
Hope, hype, and fear: the promise and potential pitfalls of artificial intelligence in criminal justice
WS Isaac
Ohio St. J. Crim. L. 15, 543, 2017
Sociotechnical Safety Evaluation of Generative AI Systems
L Weidinger, M Rauh, N Marchal, A Manzini, LA Hendricks, ...
arXiv preprint arXiv:2310.11986, 2023
Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context
D Martin Jr, V Prabhakaran, J Kuhlberg, A Smart, WS Isaac
arXiv preprint arXiv:2006.09663, 2020
Characteristics of harmful text: Towards rigorous benchmarking of language models
M Rauh, J Mellor, J Uesato, PS Huang, J Welbl, L Weidinger, S Dathathri, ...
Advances in Neural Information Processing Systems 35, 24720-24739, 2022
Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences
R Köster, KR McKee, R Everett, L Weidinger, WS Isaac, E Hughes, ...
arXiv preprint arXiv:2010.09054, 2020
Political Parties, Interest Groups, and Unequal Class Influence in American Policy
M Grossmann, Z Mahmood, W Isaac
The Journal of Politics 83 (4), 1706-1720, 2021
Science, politics and policy: how Michiganders think about the risks facing the Great Lakes
RC Hula, M Bowers, C Whitley, W Isaac
Human ecology 45, 833-844, 2017
Representation in AI Evaluations
AS Bergman, LA Hendricks, M Rauh, B Wu, W Agnew, M Kunesch, I Duan, ...
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and …, 2023
The benefits of achieving the Chesapeake Bay TMDLs (total maximum daily loads): a Scoping Study
M Cropper, WS Isaac
Statistical discrimination in learning agents
EA Duéñez-Guzmán, KR McKee, Y Mao, B Coppin, S Chiappa, ...
arXiv preprint arXiv:2110.11404, 2021
Modelling Cooperation in Network Games with Spatio-Temporal Complexity
MA Bakker, R Everett, L Weidinger, I Gabriel, WS Isaac, JZ Leibo, ...
arXiv preprint arXiv:2102.06911, 2021
The system can't perform the operation now. Try again later.
Articles 1–20