Toward trustworthy AI development: mechanisms for supporting verifiable claims M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2020 | 413 | 2020 |
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 | 388 | 2023 |
To explain or not to explain?—Artificial intelligence explainability in clinical decision support systems J Amann, D Vetter, SN Blomberg, HC Christensen, M Coffee, S Gerke, ... PLOS Digital Health 1 (2), e0000016, 2022 | 113 | 2022 |
Hard choices in artificial intelligence R Dobbe, TK Gilbert, Y Mintz Artificial Intelligence 300, 103555, 2021 | 81 | 2021 |
A broader view on bias in automated decision-making: Reflecting on epistemology and dynamics R Dobbe, S Dean, T Gilbert, N Kohli arXiv preprint arXiv:1807.00553, 2018 | 67 | 2018 |
Co-design of a trustworthy AI system in healthcare: deep learning based skin lesion classifier RV Zicari, S Ahmed, J Amann, SA Braun, J Brodersen, F Bruneault, ... Frontiers in Human Dynamics 3, 688152, 2021 | 54 | 2021 |
On assessing trustworthy AI in healthcare. Machine learning as a supportive tool to recognize cardiac arrest in emergency calls RV Zicari, J Brusseau, SN Blomberg, HC Christensen, M Coffee, ... Frontiers in Human Dynamics 3, 673104, 2021 | 39 | 2021 |
Reward reports for reinforcement learning TK Gilbert, N Lambert, S Dean, T Zick, A Snoswell, S Mehta Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 84-130, 2023 | 38 | 2023 |
Hard choices in artificial intelligence: Addressing normative uncertainty through sociotechnical commitments R Dobbe, TK Gilbert, Y Mintz arXiv preprint arXiv:1911.09005, 2019 | 25 | 2019 |
Toward trustworthy AI development: mechanisms for supporting verifiable claims (2020) M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2020 | 20 | 2020 |
Epistemic therapy for bias in automated decision-making TK Gilbert, Y Mintz Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 61-67, 2019 | 18 | 2019 |
Lessons learned from assessing trustworthy AI in practice D Vetter, J Amann, F Bruneault, M Coffee, B Düdder, A Gallucci, ... Digital Society 2 (3), 35, 2023 | 17 | 2023 |
Axes for sociotechnical inquiry in AI research S Dean, TK Gilbert, N Lambert, T Zick IEEE Transactions on Technology and Society 2 (2), 62-70, 2021 | 16 | 2021 |
Toward trustworthy AI development: Mechanisms for supporting verifiable claims. arXiv 2020 M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2004 | 16 | 2004 |
Designing Technology and Policy Simultaneously: Towards A Research Agenda and New Practice Q Yang, RY Wong, T Gilbert, MD Hagan, S Jackson, S Junginger, ... Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing …, 2023 | 15 | 2023 |
Open problems and fundamental limitations of reinforcement learning from human feedback. arXiv 2023 S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... arXiv preprint arXiv:2307.15217, 0 | 13 | |
Open problems and fundamental limitations of reinforcement learning from human feedback. CoRR, abs/2307.15217, 2023. doi: 10.48550 S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... arXiv preprint ARXIV.2307.15217, 0 | 13 | |
How to assess trustworthy AI in practice RV Zicari, J Amann, F Bruneault, M Coffee, B Düdder, E Hickman, ... arXiv preprint arXiv:2206.09887, 2022 | 11 | 2022 |
Choices, risks, and reward reports: Charting public policy for reinforcement learning systems TK Gilbert, S Dean, T Zick, N Lambert arXiv preprint arXiv:2202.05716, 2022 | 11 | 2022 |
Sociotechnical Specification for the Broader Impacts of Autonomous Vehicles TK Gilbert, AJ Snoswell, M Dennis, R McAllister, C Wu arXiv preprint arXiv:2205.07395, 2022 | 10 | 2022 |